CN116231576B - Intelligent identification method, device and equipment for fixed inspection of relay protection device - Google Patents

Intelligent identification method, device and equipment for fixed inspection of relay protection device Download PDF

Info

Publication number
CN116231576B
CN116231576B CN202310518623.7A CN202310518623A CN116231576B CN 116231576 B CN116231576 B CN 116231576B CN 202310518623 A CN202310518623 A CN 202310518623A CN 116231576 B CN116231576 B CN 116231576B
Authority
CN
China
Prior art keywords
response code
relay protection
protection device
identification
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310518623.7A
Other languages
Chinese (zh)
Other versions
CN116231576A (en
Inventor
廖峰
冯明超
杨世国
谢培奖
李土武
黄誉
黄欣欣
徐蓓
宋鹏
郑航
陈云龙
郑都
李祺
李宇恒
王友旭
廖颖欢
刘明杰
陆杰
李奇
吴海经
林汝东
陈婷
黄端华
陈臻
贺成欣
刘智驰
陈杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhanjiang Power Supply Bureau of Guangdong Power Grid Co Ltd
Original Assignee
Zhanjiang Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhanjiang Power Supply Bureau of Guangdong Power Grid Co Ltd filed Critical Zhanjiang Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority to CN202310518623.7A priority Critical patent/CN116231576B/en
Publication of CN116231576A publication Critical patent/CN116231576A/en
Application granted granted Critical
Publication of CN116231576B publication Critical patent/CN116231576B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H1/00—Details of emergency protective circuit arrangements
    • H02H1/0092—Details of emergency protective circuit arrangements concerning the data processing means, e.g. expert systems, neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H1/00—Details of emergency protective circuit arrangements
    • H02H1/0007—Details of emergency protective circuit arrangements concerning the detecting means
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Emergency Protection Circuit Devices (AREA)

Abstract

The method is used for correcting the recognition device according to response code data acquired in real time, acquiring a fixed-inspection image of a target relay protection device through the corrected recognition device, analyzing the fixed-inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to realize the intelligent recognition and judgment of a fixed-inspection result of the target relay protection device, greatly reducing basic-level artificial operation and maintenance pressure, improving working efficiency, reducing time required by working, and has the advantages of short time consumption, high efficiency, high speed, high stability and the like, thereby solving the technical problems that the conventional fixed-inspection work is required to be performed on the relay protection device, a large amount of manpower resources are required to be occupied, and the precision-benefit management requirement is not met.

Description

Intelligent identification method, device and equipment for fixed inspection of relay protection device
Technical Field
The application relates to the technical field of intelligent identification of power systems, in particular to a method, a device and equipment for intelligent identification of a relay protection device in a definite inspection mode.
Background
With the continuous development of the economic level, the power demand of the electric power is continuously increased, and the transformer stations and the electric power equipment are continuously increased. Due to the influence of various factors, the number of power operation and maintenance personnel cannot be increased proportionally with the increase of power equipment, but is gradually reduced, so that the operation and maintenance pressure is increased sharply.
In the power system, the relay protection automation team is mainly responsible for the relay protection of each transformer substation and the operation maintenance of the automation equipment, and the fixed inspection of the relay protection device is one of the most important work tasks of the relay protection automation team. When the relay protection device is subjected to fixed inspection, the signals of the relay protection device are required to be checked one by one so as to ensure the reliable operation of the equipment. The checking work needs to be carried out by two groups of personnel, one group is connected with signals on the site of the equipment, and the other group is used for observing whether the signals are correctly reported or not in a relay protection device or a background monitoring system, so that the work is simple, but the occupied personnel are more. The statistics show that the checking work of the signals of the relay protection device is at least 3 persons, and when a plurality of devices are involved, such as the main transformer is checked, even 4 to 5 persons are needed. The work occupies more staff, and the problem of insufficient hands can occur when the work task is heavy.
Disclosure of Invention
The embodiment of the application provides a method, a device and equipment for intelligently identifying the fixed inspection of a relay protection device, which are used for solving the technical problems that a large amount of human resources are required to be occupied and the requirement of lean management is not met in the prior fixed inspection work of the relay protection device.
In order to achieve the above purpose, the embodiment of the present application provides the following technical solutions:
a method for intelligently identifying the fixed inspection of a relay protection device comprises the following steps:
acquiring a fixed inspection instruction of a target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and acquiring an identification image of the target relay protection device;
identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data;
acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device;
and comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device.
Preferably, correcting the horizontal direction of the identification device according to the response code data includes:
if the response code data are a response code L and a response code R, and the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device, correcting the vertical direction of the identification module in the identification device;
If the response code data is a response code L or a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device, and acquiring the response code of the target relay protection device again until the code of the identified response code R or the response code L is consistent with the response code of the target relay protection device;
if the response code data is a response code L or a response code R, and the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, acquiring the relay protection device number and addressing data corresponding to the number of the response code in the response code data, and controlling the identification device to move to the target relay protection device according to the addressing data to acquire the identification image of the target relay protection device again;
if the response code data are not the response code L and the response code R, after waiting for the time T, the identification device is controlled again to acquire the identification image of the target relay protection device;
the step of re-controlling the identification device after waiting for the time T to obtain the identification image of the target relay protection device comprises the following steps: if the recognition device is controlled again to acquire the recognition image of the target relay protection device three times, and the obtained response code data are not the response code L and the response code R, the angle of the recognition module in the recognition device is controlled to be adjusted to the right by 90 degrees; and controlling the identification device again to acquire the identification image of the target relay protection device four times, and sending out alarm information if the obtained response code data are not the response code L and the response code R.
Preferably, adjusting the angle of the identification module in the identification device includes:
if the response code data is a response code L, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device to the right by 1 degree;
if the response code data is a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, the angle of the identification module in the identification device is adjusted to the left by 1 degrees.
Preferably, after correcting the horizontal direction of the identification device, correcting the vertical direction of the identification device according to the response code data includes:
acquiring a vertical identification image of a target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
if the vertical response code data are a response code U and a response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, completing the correction of the identification device;
if the vertical response code data is a response code U, the angle of an identification module in the identification device is downwards adjusted by 1 DEG until a response code D of a target relay protection device is identified;
If the vertical response code data is the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 degrees until the response code U of the target relay protection device is identified.
Preferably, the analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm, and obtaining the fixed inspection data of each signal lamp in the target relay protection device includes:
performing parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
constructing an identification area coordinate system according to the definite inspection image, adopting a multi-line Cheng Erfen search approximation algorithm to search and traverse each pixel from the origin of the identification area coordinate system until HSV parameter data of three continuous pixels meet constraint conditions, and then continuously traversing each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprise the number of the pixel points and coordinates of each pixel point corresponding to the number;
calculating to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data to construct a pixel matrix by taking the transverse center coordinate as a searching starting point in the positive and negative directions of the Y axis;
And obtaining the number k of signal lamps of the target relay protection device, dividing the pixel matrix into k+1 areas according to the number k of the signal lamps, and determining the fixed inspection data of each signal lamp according to the pixels of the k+1 areas.
Preferably, searching through each pixel from the origin of the identification area coordinate system by using a multi-line Cheng Erfen search approximation algorithm until HSV parameter data of three continuous pixels meets the constraint condition comprises:
traversing each pixel from the origin of the identification area coordinate system to the X-axis direction to obtain HSV parameter data of three continuous pixels to meet constraint conditions;
if each pixel is traversed from the origin of the identification area coordinate system to the X-axis direction, and the HSV parameter data of three continuous pixels cannot meet the constraint condition, traversing each pixel from the positive direction thread and the negative direction thread of the Y-axis along the X-axis direction by adopting a multithreading binary search approximation algorithm until the HSV parameter data of three continuous pixels exist in any one direction thread and meet the constraint condition.
The application also provides a fixed-inspection intelligent recognition device of the relay protection device, which comprises a data acquisition module, a recognition correction module, a fixed-inspection analysis module and a comparison output module;
The data acquisition module is used for acquiring a fixed inspection instruction of the target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction and acquiring an identification image of the target relay protection device;
the identification correction module is used for identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data;
the fixed inspection analysis module is used for acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device;
and the comparison output module is used for comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain the fixed inspection result of the target relay protection device.
Preferably, the identification correction module includes a horizontal correction sub-module and a vertical correction sub-module:
the horizontal correction submodule is used for correcting the vertical direction of the identification module in the identification device according to the response code data, namely a response code L and a response code R, wherein the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device;
Or according to the response code data being a response code L or a response code R, and the number of the response code in the response code data being consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device, and obtaining the response code of the target relay protection device again until the identified response code R or the response code L is consistent with the response code of the target relay protection device;
or according to the response code data being a response code L or a response code R, wherein the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, the relay protection device number and addressing data corresponding to the number of the response code in the response code data are obtained, and the identification device is controlled to move to the target relay protection device according to the addressing data to re-obtain the identification image of the target relay protection device;
or according to the response code data not being the response code L and the response code R, after waiting time T, re-controlling the identification device to acquire the identification image of the target relay protection device;
the vertical correction sub-module is used for acquiring a vertical identification image of the target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
According to the vertical response code data, namely a response code U and a response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, completing the correction of the identification device;
or according to the vertical response code data as a response code U, the angle of an identification module in the identification device is downwards adjusted by 1 DEG until the response code D of the target relay protection device is identified;
or according to the vertical response code data as the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 degrees until the response code U of the target relay protection device is identified.
Preferably, the fixed-inspection analysis module comprises a pixel conversion sub-module, a search traversing sub-module, a calculation sub-module and a fixed-inspection sub-module;
the pixel conversion sub-module is used for carrying out parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
the searching traversing submodule is used for constructing an identification area coordinate system according to the fixed-inspection image, searching and traversing each pixel from the origin of the identification area coordinate system by adopting a multi-line Cheng Erfen searching approximation algorithm until HSV parameter data of three continuous pixels meet constraint conditions, and then continuing to traverse each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprise the number of the pixel points and coordinates of each pixel point corresponding to the number;
The calculation submodule is used for calculating to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data to construct a pixel matrix by taking the transverse center coordinate as a searching starting point in the positive and negative directions of the Y axis;
the fixed inspection sub-module is used for obtaining the number k of signal lamps of the target relay protection device, dividing the pixel matrix into k+1 areas according to the number k of the signal lamps, and determining fixed inspection data of each signal lamp according to the pixels of the k+1 areas.
The application also provides a terminal device, which comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
and the processor is used for executing the intelligent identification method for the fixed check of the relay protection device according to the instruction in the program code.
From the above technical solutions, the embodiments of the present application have the following advantages: the method comprises the steps of obtaining a fixed inspection instruction of a target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and obtaining an identification image of the target relay protection device; identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data; acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device; and comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device. According to the method for intelligently identifying the fixed inspection of the relay protection device, response code data obtained in real time are used for correcting the identification device, the corrected identification device is used for obtaining a fixed inspection image of the target relay protection device, the multi-line Cheng Erfen search approximation algorithm is used for analyzing the fixed inspection image to realize the intelligent identification and judgment of the fixed inspection result of the target relay protection device, the manual operation and maintenance pressure of a base layer is greatly reduced, the working efficiency is improved, the time required by the work is shortened, the advantages of short time consumption, high efficiency, high speed, high stability and the like are achieved, and the technical problems that the conventional fixed inspection work of the relay protection device needs to occupy a large amount of manpower resources and the requirement of lean management is not met are solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a step flowchart of a method for identifying a relay protection device according to an embodiment of the present application;
fig. 2 is a frame diagram of an identification device in the method for identifying a relay protection device in a fixed inspection intelligent manner according to an embodiment of the present application;
fig. 3 is a schematic diagram of a machine room of the relay protection device in the method for intelligently identifying the relay protection device by the fixed inspection according to the embodiment of the application;
fig. 4 is a schematic diagram of an identification area of a relay protection device in a method for intelligently identifying a fixed inspection of the relay protection device according to an embodiment of the present application;
fig. 5 is a frame diagram of a fixed inspection intelligent recognition device of a relay protection device in an embodiment of the application.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Patent term interpretation of the present application:
and (3) relay protection device: an automated measure and apparatus for timely alerting an operator on duty or directly issuing a trip command to a controlled circuit breaker to terminate the development of such events when a power element (e.g., generator, line, etc.) in the power system or the power system itself fails, jeopardizing the safe operation of the power system.
The transformer substation background monitoring system uses a computer, communication equipment and a measurement and control unit as basic tools, provides a basic platform for real-time data acquisition, switch state detection and remote control of a transformer substation power distribution system, can form any complex monitoring system with detection and control equipment, plays a core role in transformer substation power distribution monitoring, can help enterprises to eliminate islanding, reduce operation cost, improve production efficiency and accelerate abnormal reaction speed in a transformer substation power distribution process.
AS32 communication module: the AS32 communication module transmits data with the working frequency of 433M, adopts the SAW frequency stabilization of the acoustic surface resonator, has extremely high frequency stability, and only 3 ppm/degree of frequency drift when the ambient temperature changes between minus 25 degrees and plus 85 degrees, and is mainly used for controlling robots.
multisim is a Windows-based simulation tool developed by National Instruments (NI) limited and is suitable for board-level analog/digital circuit board design work. It includes the graphic input of circuit schematic diagram and the input mode of circuit hardware description language.
The 8051 single chip microcomputer is an 8-bit single chip microcontroller, belongs to one of MCS-51 single chips, and is manufactured by Intel corporation in 1981. The INTEL corporation delegates the core technology of MCS51 to many other companies, so many companies are doing 8051-core single-chip computers, such as Atmel, philips, deep-united-china, and the like, and successively develop compatible products with more functions and more power.
The embodiment of the application provides a method, a device and equipment for intelligently identifying the fixed inspection of a relay protection device, which can quickly intelligently identify and judge the fixed inspection result of the relay protection device, greatly reduce the manual operation and maintenance pressure of a base layer, improve the working efficiency, reduce the time required by the work, have the advantages of short time consumption, high efficiency, high speed, high stability and the like, and simultaneously can also provide great convenience for the daily maintenance of the secondary equipment of a transformer substation through the fixed inspection identification method of the protection device, effectively and directly reduce the workload of operation and maintenance personnel of the base layer, improve the intelligent level of the operation and maintenance of the transformer substation, and are used for solving the technical problems that the relay protection device is subjected to fixed inspection work, occupies a large amount of manpower resources and does not meet the requirement of lean management.
Embodiment one:
fig. 1 is a step flowchart of a method for intelligently identifying a fixed inspection of a relay protection device according to an embodiment of the present application, fig. 2 is a frame diagram of an identification device in the method for intelligently identifying a fixed inspection of a relay protection device according to an embodiment of the present application, and fig. 3 is a schematic diagram of a machine room of a relay protection device in the method for intelligently identifying a fixed inspection of a relay protection device according to an embodiment of the present application.
As shown in fig. 2, in the embodiment of the present application, the identification device includes a control module, and a direct current module, a communication module, an acquisition module, a translation module, and a mechanical module that are connected with the control module. The direct current module is used for providing power for the control module, the communication module and the acquisition module.
It should be noted that, the direct current module provides power through lithium battery. The communication module can realize communication through the SX1278 module, and the acquisition module can realize acquisition of images of the target relay protection device through the high-definition intelligent network camera. The translation module may effect movement of the identification device through the Mecanum wheel chassis. The mechanical module is used for realizing 3D autonomous printing. The control module can control the operation of the acquisition module, the translation module and the mechanical module through the STC12C5A60S2 singlechip. The identification device is of a mechanical structure printed by a 3D printing technology, a communication module is selected to be combined with a control module, a network camera remote monitoring technology of a collecting module is matched, movement control of a Mecanum wheel chassis is assisted, operation of an auxiliary system of a power distribution network and acquisition of pictures of a transformer substation monitoring system and a relay protection device are achieved, and accordingly fixed inspection of the relay protection device is assisted.
As shown in fig. 3, in the embodiment of the present application, in the machine room, the identification device is located at a left side of the machine room, and the database of addressing data of the relay protection device is set again through data such as an angle distance measured in the field, and route data of the identification device from a departure point to a destination relay protection device is stored in the database. When the identification device receives the checking instruction, the position number of the relay protection device is analyzed, and the identification device automatically starts the target relay protection device.
It should be noted that, the addressing data adopts hexadecimal coding mechanism, and a bit hexadecimal code is set for each relay protection device, and the code is also a node of the route. As shown in fig. 3, the initial position of the identification device is set to be a, the relay protection device No. 0 is set to be 0, and so on, and specific addressing data are shown in table 1.
In the embodiment of the present application, the packet of the check instruction may include: a checkup instruction of 101, a checkup instruction of 102, a checkup instruction of 103, and a checkup instruction of 104.
It should be noted that, the fixed inspection instruction of 101 refers to starting the relay protection device to automatically address and automatically reach the target relay protection device. 102 refers to manual control instructions. 103 refers to returning to the origin. 104 refers to the occurrence of an error.
In this embodiment of the present application, the packet of the checking instruction may further include:
fixed check instruction of 1001: the first relay protection device, i.e. relay protection device No. 0 in fig. 3.
...
A checkpointed instruction of 1010: tenth relay protection device, namely, the relay protection device No. 9 in fig. 3.
2001 checkup instruction: the manual control is stopped.
The checkup instruction of 2002: left turn.
A checkpost instruction of 2003: and (5) turning right.
A checkup instruction of 2004: and (5) backing.
It should be noted that, the fixed inspection instruction, for example 1011001, is to start the relay protection device to automatically address and then automatically go to the relay protection device No. 0. The fixed inspection instruction of 1022004 is to manually control the auxiliary trolley to retreat.
As shown in fig. 1, an embodiment of the present application provides a method for identifying a relay protection device by using a fixed inspection intelligent method, including the following steps:
s1, acquiring a fixed inspection instruction of a target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and acquiring an identification image of the target relay protection device.
In step S1, the identification device is controlled to move to the target relay protection device according to the inspection instruction to obtain the identification image. In this embodiment, after the identification device is controlled to move to the target relay protection device according to the fixed inspection instruction, the horizontal angle and the vertical angle of the acquisition module of the identification device are controlled to be adjusted to initial default positions, and then the identification image of the target relay protection device is acquired. Wherein, initial default position is: horizontal angle 0 ° and vertical angle 0 °.
S2, identifying the identification image by using OpenCV to obtain response code data; the horizontal direction and the vertical direction of the recognition device are corrected based on the response code data.
In step S2, the response code in the identification image is already the response code in the identification image; secondly, correcting an acquisition module of the identification device according to the response code data, and ensuring that the acquired fixed-inspection image is an image in a fixed-inspection area of the target relay protection device. The response code is arranged on the target relay protection device.
S3, acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device.
In step S3, after determining that the four quick response codes are all in the checking area of the target relay protection device according to the corrected recognition device, the checking pattern is obtained to recognize the checking result. And analyzing the fixed inspection image through a multi-thread binary search approximation algorithm to realize quick identification of the fixed inspection result of the target relay protection device.
S4, comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device.
In the step S4, the inspection data of each signal lamp in the target relay protection device is obtained according to the step S3 and compared with the normal data of the signal lamp corresponding to the target relay protection device, so as to obtain the inspection result of the target relay protection device. In this embodiment, if the fixed inspection data is that the color of the signal lamp is black, red, and black, and the normal data corresponding to the color of the signal lamp is black, red, and black, the comparison results of the two are consistent, which indicates that the target relay protection device is normal. And if the fixed detection data of the signal lamp of the target relay protection device is inconsistent with the normal data of the corresponding signal lamp, indicating that the target relay protection device is abnormal.
The method comprises the steps of obtaining a fixed inspection instruction of a target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and obtaining an identification image of the target relay protection device; identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data; acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device; and comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device. According to the method for intelligently identifying the fixed inspection of the relay protection device, response code data obtained in real time are used for correcting the identification device, the corrected identification device is used for obtaining a fixed inspection image of the target relay protection device, the multi-line Cheng Erfen search approximation algorithm is used for analyzing the fixed inspection image to realize the intelligent identification and judgment of the fixed inspection result of the target relay protection device, the manual operation and maintenance pressure of a base layer is greatly reduced, the working efficiency is improved, the time required by the work is shortened, the advantages of short time consumption, high efficiency, high speed, high stability and the like are achieved, and the technical problems that the conventional fixed inspection work of the relay protection device needs to occupy a large amount of manpower resources and the requirement of lean management is not met are solved.
It should be noted that the method for intelligently identifying the fixed inspection of the relay protection device can also be applied to the inspection and operation and maintenance of secondary equipment of a transformer substation, provides great convenience for daily maintenance of equipment in a power system, can effectively and directly reduce the workload of basic-level operation and maintenance personnel, and improves the intelligent level of operation and maintenance of the transformer substation.
In one embodiment of the present application, correcting the horizontal direction of the identification device based on the response code data includes:
if the response code data are a response code L and a response code R, and the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device, correcting the vertical direction of the identification module in the identification device;
if the response code data is a response code L or a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, adjusting the angle of the identification module in the identification device, and acquiring the response code of the target relay protection device again until the identified response code R or the response code L is consistent with the response code of the target relay protection device;
if the response code data is a response code L or a response code R, and the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, acquiring the relay protection device number and addressing data corresponding to the number of the response code in the response code data, and controlling the identification device to move to the target relay protection device according to the addressing data so as to acquire the identification image of the target relay protection device again;
If the response code data are not the response code L and the response code R, after waiting for the time T, re-controlling the identification device to acquire the identification image of the target relay protection device;
the step of re-controlling the identification device after waiting for the time T to obtain the identification image of the target relay protection device comprises the following steps: if the recognition device is controlled again to acquire the recognition image of the target relay protection device three times, and the obtained response code data are not the response code L and the response code R, the angle of the recognition module in the recognition device is controlled to be adjusted to the right by 90 degrees; and controlling the identification device again to acquire the identification image of the target relay protection device four times, and sending out alarm information if the obtained response code data are not the response code L and the response code R.
In this embodiment of the present application, adjusting an angle of an identification module in an identification device includes:
if the response code data is a response code L, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, the angle of an identification module in the identification device is adjusted to the right by 1 degree;
if the response code data is a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, the angle of the identification module in the identification device is adjusted to the left by 1 degrees.
It should be noted that, according to the identification image, openCV is adopted to identify the response code L and the response code R of the target relay protection device first, and according to the identified response code L and/or response code R, the identification module of the identification device is horizontally corrected. In this embodiment, the response code data obtained by recognition is a response code L and a response code R, and the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device, and then the next operation is performed, that is, the vertical direction of the recognition module in the recognition device is corrected. And the response code data obtained by recognition is only a response code L, and the number of the relay protection device in the response code L accords with the actual number of the target relay protection device, then the recognition module of the recognition device is rotated to the right by an angle of 1 degree, the recognition module of the recognition device is started again until the response code R is recognized, and the number of the relay protection device in the response code R accords with the actual number of the target relay protection device, and then the next operation is carried out, namely the vertical direction of the recognition module in the recognition device is corrected. The identified response code data is only a response code L, the relay protection device number in the response code L is not consistent with the actual number of the target relay protection device, the relay protection device number in the response code L is obtained, the path to the target relay protection device is obtained through automatic addressing data, and the operation is performed again according to the step S1 after the path reaches the correct position. And the response code data obtained by recognition is only a response code R, and the number of the relay protection device in the response code R accords with the actual number of the target relay protection device, then the recognition module of the recognition device is rotated leftwards by an angle of 1 degree, the recognition module of the recognition device is started again until the response code L is recognized, and the number of the relay protection device in the response code L accords with the actual number of the target relay protection device, and then the next operation is carried out, namely the vertical direction of the recognition module in the recognition device is corrected. The identified response code data is only a response code R, the relay protection device number in the response code R is not consistent with the actual number of the target relay protection device, the relay protection device number in the response code R is obtained, the path to the target relay protection device is obtained through automatic addressing data, and the operation is performed again according to the step S1 after the path reaches the correct position. The identified data are not the response code L and the response code R, and after 30 seconds, the step S1 is restarted and is executed for three times; if the identification module of the identification device still cannot be identified, turning the identification module of the identification device to the right by an angle of 90 degrees, starting the step S1 again, and executing four times; if the identification is still impossible, sending out alarm information and performing manual intervention. Wherein the time T may be 30s.
In one embodiment of the present application, correcting the vertical direction of the recognition device according to the response code data after correcting the horizontal direction of the recognition device includes:
acquiring a vertical identification image of the target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
if the vertical response code data are the response code U and the response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, the correction of the identification device is completed;
if the vertical response code data is the response code U, the angle of an identification module in the identification device is downwards adjusted by 1 DEG until the response code D of the target relay protection device is identified;
if the vertical response code data is the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 DEG until the response code U of the target relay protection device is identified.
After correcting the horizontal direction of the recognition device, it is described that the horizontal correction of the recognition module in the recognition device is completed, and the response code L and the response code R are already located in the image area acquired by the recognition device, so that the recognition module of the recognition device can be vertically corrected. And starting an identification module of the identification device to acquire an identification image, and identifying the response code U and the response code D according to the identification image. Because the response codes L and R are already positioned in the acquired image area, according to the position relation of the four response codes, the condition that the response codes U and D are not positioned in the image area at the same time can not occur. If the vertical response code data are identified as the response code U and the response code D, and the numbers of the relay protection devices in the response code U and the response code D are consistent with the actual numbers of the target relay protection devices, then step S3 is performed. Because the identification codes L and R determine that the numbers of the relay protection devices are consistent with the actual numbers of the target relay protection devices, the numbers of the relay protection devices in the identification codes U and D are necessarily consistent with the actual numbers of the target relay protection devices. If the vertical response code data obtained by recognition is only the response code U, the recognition module of the recognition device is rotated downwards by an angle of 1 degrees, the recognition module of the recognition device is started again until the response code D is recognized, and the next operation is performed, namely, the step S3 is executed. If the vertical response code data obtained by recognition is only the response code D, the recognition module of the recognition device is rotated upwards by an angle of 1 degrees, the recognition module of the recognition device is started again until the response code U is recognized, and the next operation is performed, namely, the step S3 is executed.
Fig. 4 is a schematic diagram of an identification area of a relay protection device in the method for intelligently identifying the relay protection device by the fixed inspection according to the embodiment of the application.
In one embodiment of the present application, analyzing the fixed inspection image by using a multi-line Cheng Erfen search approximation algorithm, the obtaining the fixed inspection data of each signal lamp in the target relay protection device includes:
performing parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
constructing an identification area coordinate system according to the definite inspection image, adopting a multi-line Cheng Erfen search approximation algorithm to search and traverse each pixel from the origin of the identification area coordinate system until HSV parameter data of three continuous pixels meet constraint conditions, and then continuing to traverse each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprises the number of the pixel points and coordinates of each pixel point corresponding to the number;
calculating to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data in the positive and negative directions of the Y axis by taking the transverse center coordinate as a searching starting point to construct a pixel matrix;
the method comprises the steps of obtaining the number k of signal lamps of a target relay protection device, dividing a pixel matrix into k+1 areas according to the number k of the signal lamps, and determining the fixed inspection data of each signal lamp according to pixels of the k+1 areas;
The method for searching and traversing each pixel from the origin of the identification area coordinate system by adopting a multithreading binary search approximation algorithm until HSV parameter data of three continuous pixels meet constraint conditions comprises the following steps:
traversing each pixel from the origin of the identification area coordinate system to the X-axis direction to obtain HSV parameter data of three continuous pixels to meet constraint conditions;
if each pixel is traversed from the origin of the identification area coordinate system to the X-axis direction, and the HSV parameter data of three continuous pixels cannot meet the constraint condition, traversing each pixel from the positive direction thread and the negative direction thread of the Y-axis along the X-axis direction by adopting a multithreading binary search approximation algorithm until the HSV parameter data of three continuous pixels exist in any one direction thread and meet the constraint condition.
It should be noted that, after determining that the four response codes L, R, U, D are all in the image area of the target relay protection device in step S2, the identification module of the identification device obtains the calibration image, and then the calibration image is processed and analyzed by adopting the multi-line Cheng Erfen search approximation algorithm to obtain the calibration data of the target relay protection device. As shown in fig. 4, in the image area of the target relay protection device, the signal lamp has two states of on and off, the signal lamp is on in red, and the signal lamp is off in black. The response code is black in color, and two blue round stickers with the same size as the signal lamp are posted at the head end and the tail end of the signal lamp to serve as the starting point and the end point of the signal lamp for convenience in recognition. The other areas of the image are black and white in tone. The acquired inspection data mainly identifies the color of the signal lamp in the inspection image.
In the embodiment of the application, the acquired calibration image is a color image, and the color image matrix is composed of red, green and blue 3-color channel RGB matrixes. Since only the signal lamp is lighted to be red in the acquired inspection image, the signal lamp state can be distinguished by detecting and analyzing the red area of the inspection image. The intelligent identification method for the relay protection device comprises the steps of judging a fixed inspection image through an HSV color model, converting the fixed inspection image from an RGB color space to an HSV color space, and screening by setting H parameter data ranges (0, 10) and (156, 180), S parameter data ranges (43, 255) and V parameter data ranges (46, 255), wherein a screening result is a red signal lamp area.
It should be noted that HSV is a color space created by a.r. Smith in 1978, also called hexagonal pyramid Model (Hexcone Model), based on the intuitive nature of colors. The HSV color model refers to a subset of visible light in the H, S, V three-dimensional color space that contains all the colors of a certain color gamut. In this embodiment, as shown in fig. 4, the method for intelligently identifying the fixed inspection of the relay protection device includes firstly dividing the fixed inspection image into two parts in the Y-axis direction with the X-axis as a dividing line in average: and Y1 and Y2, adopting two threads to search two areas of Y1 and Y2 respectively at the same time, and judging HSV parameter data of each pixel. The X, T axial direction and the signal lamp arrangement position are that the signal lamps are arranged in the same longitudinal column, if searching is performed in the X-axis direction, only one searching target is needed; if the search is performed in the Y-axis direction, the search targets are multiple (multiple signal lamps), and the probability of finding the signal lamp by the X-axis search is higher, the efficiency is higher, and the speed is higher.
In the embodiment of the application, each pixel is traversed from the origin of the identification area coordinate system to the X-axis direction, so that HSV parameter data of three continuous pixels are obtained to meet constraint conditions. Specifically, the coordinates of the search pixel point are (X, y), and first, pixels of y=0 rows are traversed in order along the X axis from the origin (0, 0) of coordinates, and the formula constraint condition is determined for each pixel. When 3 pixel points meeting the constraint condition continuously appear, judging the identification area of the red signal lamp or the blue signal lamp meeting the constraint condition, and recording the coordinate of the first pixel point meeting the first formula in the constraint condition as (redx) 1 ，redy 1 ) Recording the first pixel point coordinate satisfying the second formula in the constraint condition as (blue 1 ，bluey 1 ). The constraint condition comprises a first formula of a red signal lamp and a second formula of a blue signal lamp, wherein the first formula is as follows:
；
the second formula is:
。
in the embodiment of the present application, if the X-axis direction is from the origin of the identification area coordinate systemIf HSV parameter data of three continuous pixels cannot be obtained by traversing each pixel and the HSV parameter data meets constraint conditions, two search pixel point coordinate parameters (x 1 ，y 1 ）、（x 2 ，y 2 ) For both threads to search at the same time. Executing y using forward line direction threads 1 =y 1 +1, searching for pixels in the second row above, traversing from left to right sequentially along the X-axis. At the same time, the negative direction thread is adopted to simultaneously execute y 2 =y 2 -1, searching for pixels of the second row down, traversing from left to right in sequence along the X-axis. The first and second formulas are also determined for each pixel searched. When 3 pixel points meeting the constraint condition continuously appear, judging the identification area of the red signal lamp or the blue signal lamp meeting the constraint condition, and recording the coordinate of the first pixel point meeting the constraint condition as (redx) 1 ，redy 1 ) Recording the pixel point coordinates of the first second formula meeting the constraint condition as (blue 1 ，bluey 1 ). The search is continuously and circularly executed until any direction thread finds the pixel points meeting the constraint condition. When the pixel points meeting the constraint conditions are found, the X-axis direction traversal is continued until the pixel points (redx) which do not meet the first formula or the second formula are found again n+1 ，redy m ) Or (blue) n+1 ，bluey m ) And obtaining pixel point data.
The method for intelligently identifying the fixed inspection of the relay protection device is characterized in that a transverse center coordinate and a longitudinal center coordinate are obtained through calculation according to pixel point data. Such as: based on (redx) 1 ，redy m ) To (redx) n ，redy m ) The coordinate variation range of the pixel point is 1-n, the center is n/2, so the transverse center coordinate of the marking area of the color transmitting signal lamp is (redx) n/2 ，redy m ) The transverse center coordinate of the blue signal lamp identification area obtained by the same method is. The content of calculating the longitudinal center coordinates includes: fix the search point abscissa to +.>Continuing searching for the upper row y=y+1 or the lower row y=y-1 until the pixel point which does not meet the first formula or the second formula is found againOr->The longitudinal center point coordinates of the signal lamp or the sign can be determined>Or->And the number of pixels of the longitudinal maximum range of the signal lamp or the identification patch is recorded as m.
In the embodiment of the application, the abscissa search starting point is taken asThe vertical coordinate search starting point is redy m+1 Or blue m+1 Continuing searching up to one row y=y+1 or the next row y=y-1, recording the color of the pixel point of each coordinate, storing the color in a matrix c1 and a matrix c2, and finally synthesizing the matrix c1 and the matrix c2 into a pixel matrix c, wherein the pixel matrix c stores the horizontal coordinate as->The pixel point color value of the column.
In the embodiment of the present application, the content of the calibration data of each signal lamp is determined according to the pixels of k+1 areas: if the length of the pixel matrix c is recorded as lThe number of signal lamps of the target relay protection device is recorded as k, so that the pixel matrix c can be divided into k+1 areas according to the signal lamps, and the first k areas are divided into a plurality of areaslM)/k pixels, the last region consisting of m pixels. The head area of the fixed inspection image area of the target relay protection device is [0, -1]And tail region [l-m，l-1]Blue mark part from bottom to topThe color of a signal lamp is [ (] in the pixel matrix cl-m）/k，2*（l-m）/k-1]Part, the color of the g signal lamp is [ (] in the pixel matrix cl-m）/k，（g+1）*（l-m）/k-1]Part(s). The checkpointed data of each signal lamp is composed of pixel point color values of the pixel matrix. Wherein g is a natural number less than k.
Embodiment two:
fig. 5 is a frame diagram of a fixed inspection intelligent recognition device of a relay protection device in an embodiment of the application.
As shown in fig. 5, an embodiment of the present application provides a device for identifying a relay protection device by checking and intelligently identifying, including: the system comprises a data acquisition module 10, an identification correction module 20, a fixed-inspection analysis module 30 and a comparison output module 40;
the data acquisition module 10 is used for acquiring a fixed inspection instruction of the target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and acquiring an identification image of the target relay protection device;
The recognition correction module 20 is configured to recognize the recognition image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data;
the fixed inspection analysis module 30 is configured to obtain a fixed inspection image of the target relay protection device through the corrected identification device, and analyze the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device;
and the comparison output module 40 is used for comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain the fixed inspection result of the target relay protection device.
In the present embodiment, the identification correction module 20 includes a horizontal correction sub-module and a vertical correction sub-module;
the horizontal correction sub-module is used for correcting the vertical direction of the identification module in the identification device according to the response code data, namely a response code L and a response code R, wherein the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device;
or according to the response code data being the response code L or the response code R, and the number of the response code in the response code data being consistent with the response code of the target relay protection device, adjusting the angle of the identification module in the identification device, and obtaining the response code of the target relay protection device again until the identified response code R or the response code L is consistent with the response code of the target relay protection device;
Or according to the response code data being the response code L or the response code R, wherein the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, the relay protection device number and addressing data corresponding to the number of the response code in the response code data are obtained, and the identification device is controlled to move to the target relay protection device according to the addressing data to acquire the identification image of the target relay protection device again;
or according to the response code data not being the response code L and the response code R, after waiting time T, re-controlling the identification device to obtain the identification image of the target relay protection device;
the vertical correction sub-module is used for acquiring a vertical identification image of the target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
according to the vertical response code data, namely a response code U and a response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, completing the correction of the identification device;
or the angle of the identification module in the identification device is downwards adjusted by 1 DEG according to the vertical response code data as the response code U until the response code D of the target relay protection device is identified;
Or according to the vertical response code data as the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 degrees until the response code U of the target relay protection device is identified.
In the embodiment of the present application, the fixed inspection analysis module 30 includes a pixel conversion sub-module, a search traversal sub-module, a calculation sub-module, and a fixed inspection sub-module;
the pixel conversion sub-module is used for carrying out parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
the searching traversing submodule is used for constructing an identification area coordinate system according to the fixed-inspection image, searching and traversing each pixel from the origin of the identification area coordinate system by adopting a multi-line Cheng Erfen searching and approximating algorithm until HSV parameter data of three continuous pixels meet constraint conditions, and then continuing to traverse each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprises the number of the pixel points and coordinates of each pixel point corresponding to the number;
the computing sub-module is used for computing to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data to construct a pixel matrix by taking the transverse center coordinate as a searching starting point in the positive and negative directions of the Y axis;
The fixed inspection sub-module is used for obtaining the number k of the signal lamps of the target relay protection device, dividing the pixel matrix into k+1 areas according to the number k of the signal lamps, and determining the fixed inspection data of each signal lamp according to the pixels of the k+1 areas.
It should be noted that, the modules in the second device correspond to the steps in the method in the first embodiment, the content of the method for identifying the relay protection device by the inspection intelligence is described in detail in the first embodiment, and the content of the modules in the second embodiment is not described in detail in the second embodiment.
Example III
The embodiment of the application provides terminal equipment, which comprises a processor and a memory;
a memory for storing program code and transmitting the program code to the processor;
and the processor is used for executing the intelligent identification method for the fixed check of the relay protection device according to the instruction in the program code.
It should be noted that, the processor is configured to execute the steps in the above-mentioned embodiment of the method for identifying the relay protection device by using the instruction in the program code. In the alternative, the processor, when executing the computer program, performs the functions of the modules/units in the system/apparatus embodiments described above.
For example, a computer program may be split into one or more modules/units, which are stored in a memory and executed by a processor to complete the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the terminal device.
The terminal device may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the terminal device is not limited and may include more or less components than those illustrated, or may be combined with certain components, or different components, e.g., the terminal device may also include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used for storing computer programs and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or is to be output.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims (8)

1. The intelligent identification method for the fixed inspection of the relay protection device is characterized by comprising the following steps of:
acquiring a fixed inspection instruction of a target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction, and acquiring an identification image of the target relay protection device;
identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data;
acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device;
Comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device;
analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm, wherein the obtaining of the fixed inspection data of each signal lamp in the target relay protection device comprises the following steps:
performing parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
constructing an identification area coordinate system according to the definite inspection image, adopting a multi-line Cheng Erfen search approximation algorithm to search and traverse each pixel from the origin of the identification area coordinate system until HSV parameter data of three continuous pixels meet constraint conditions, and then continuously traversing each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprise the number of the pixel points and coordinates of each pixel point corresponding to the number;
calculating to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data to construct a pixel matrix by taking the transverse center coordinate as a searching starting point in the positive and negative directions of the Y axis;
and obtaining the number k of signal lamps of the target relay protection device, dividing the pixel matrix into k+1 areas according to the number k of the signal lamps, and determining the fixed inspection data of each signal lamp according to the pixels of the k+1 areas.
2. The method for intelligently identifying the relay protection device by the fixed inspection according to claim 1, wherein correcting the horizontal direction of the identification device according to the response code data comprises:
if the response code data are a response code L and a response code R, and the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device, correcting the vertical direction of the identification module in the identification device;
if the response code data is a response code L or a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device, and acquiring the response code of the target relay protection device again until the code of the identified response code R or the response code L is consistent with the response code of the target relay protection device;
if the response code data is a response code L or a response code R, and the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, acquiring the relay protection device number and addressing data corresponding to the number of the response code in the response code data, and controlling the identification device to move to the target relay protection device according to the addressing data to acquire the identification image of the target relay protection device again;
If the response code data are not the response code L and the response code R, after waiting for the time T, the identification device is controlled again to acquire the identification image of the target relay protection device;
the step of re-controlling the identification device after waiting for the time T to obtain the identification image of the target relay protection device comprises the following steps: if the recognition device is controlled again to acquire the recognition image of the target relay protection device three times, and the obtained response code data are not the response code L and the response code R, the angle of the recognition module in the recognition device is controlled to be adjusted to the right by 90 degrees; and controlling the identification device again to acquire the identification image of the target relay protection device four times, and sending out alarm information if the obtained response code data are not the response code L and the response code R.
3. The method for intelligently identifying the relay protection device by the fixed inspection according to claim 2, wherein adjusting the angle of the identification module in the identification device comprises:
if the response code data is a response code L, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device to the right by 1 degree;
if the response code data is a response code R, and the number of the response code in the response code data is consistent with the response code of the target relay protection device, the angle of the identification module in the identification device is adjusted to the left by 1 degrees.
4. The method for intelligently identifying the relay protection device by the fixed inspection according to claim 2, wherein after correcting the horizontal direction of the identification device, correcting the vertical direction of the identification device according to the response code data comprises:
acquiring a vertical identification image of a target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
if the vertical response code data are a response code U and a response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, completing the correction of the identification device;
if the vertical response code data is a response code U, the angle of an identification module in the identification device is downwards adjusted by 1 DEG until a response code D of a target relay protection device is identified;
if the vertical response code data is the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 degrees until the response code U of the target relay protection device is identified.
5. The method for intelligently identifying the fixed inspection of the relay protection device according to claim 1, wherein the steps of searching through each pixel from the origin of the identification area coordinate system by adopting a multi-thread binary search approximation algorithm until the HSV parameter data of three continuous pixels meet the constraint condition comprise the following steps:
Traversing each pixel from the origin of the identification area coordinate system to the X-axis direction to obtain HSV parameter data of three continuous pixels to meet constraint conditions;
if each pixel is traversed from the origin of the identification area coordinate system to the X-axis direction, and the HSV parameter data of three continuous pixels cannot meet the constraint condition, traversing each pixel from the positive direction thread and the negative direction thread of the Y-axis along the X-axis direction by adopting a multithreading binary search approximation algorithm until the HSV parameter data of three continuous pixels exist in any one direction thread and meet the constraint condition.
6. Intelligent identification device is examined to relay protection device's surely, its characterized in that includes: the device comprises a data acquisition module, an identification correction module, a fixed inspection analysis module and a comparison output module;
the data acquisition module is used for acquiring a fixed inspection instruction of the target relay protection device, controlling the identification device to move to the target relay protection device according to the fixed inspection instruction and acquiring an identification image of the target relay protection device;
the identification correction module is used for identifying the identification image by using OpenCV to obtain response code data; correcting the horizontal direction and the vertical direction of the identification device according to the response code data;
The fixed inspection analysis module is used for acquiring a fixed inspection image of the target relay protection device through the corrected identification device, and analyzing the fixed inspection image by adopting a multi-line Cheng Erfen search approximation algorithm to obtain fixed inspection data of each signal lamp in the target relay protection device;
the comparison output module is used for comparing the fixed inspection data of each signal lamp with the normal data of the corresponding signal lamp to obtain a fixed inspection result of the target relay protection device;
the fixed-inspection analysis module comprises a pixel conversion sub-module, a search traversing sub-module, a calculation sub-module and a fixed-inspection sub-module;
the pixel conversion sub-module is used for carrying out parameter conversion on the fixed inspection image by adopting an HSV color model to obtain HSV parameter data corresponding to each pixel in the fixed inspection image;
the searching traversing submodule is used for constructing an identification area coordinate system according to the fixed-inspection image, searching and traversing each pixel from the origin of the identification area coordinate system by adopting a multi-line Cheng Erfen searching approximation algorithm until HSV parameter data of three continuous pixels meet constraint conditions, and then continuing to traverse each pixel until the HSV parameter data of the pixels do not meet the constraint conditions, so as to obtain pixel point data; the pixel point data comprise the number of the pixel points and coordinates of each pixel point corresponding to the number;
The calculation submodule is used for calculating to obtain a transverse center coordinate according to the pixel point data, and searching the pixel point data to construct a pixel matrix by taking the transverse center coordinate as a searching starting point in the positive and negative directions of the Y axis;
the fixed inspection sub-module is used for obtaining the number k of signal lamps of the target relay protection device, dividing the pixel matrix into k+1 areas according to the number k of the signal lamps, and determining fixed inspection data of each signal lamp according to the pixels of the k+1 areas.
7. The intelligent identification device for the relay protection device according to claim 6, wherein the identification correction module comprises a horizontal correction sub-module and a vertical correction sub-module;
the horizontal correction submodule is used for correcting the vertical direction of the identification module in the identification device according to the response code data, namely a response code L and a response code R, wherein the numbers of the response code L and the response code R are consistent with the response code codes of the target relay protection device;
or according to the response code data being a response code L or a response code R, and the number of the response code in the response code data being consistent with the response code of the target relay protection device, adjusting the angle of an identification module in the identification device, and obtaining the response code of the target relay protection device again until the identified response code R or the response code L is consistent with the response code of the target relay protection device;
Or according to the response code data being a response code L or a response code R, wherein the number of the response code in the response code data is inconsistent with the response code of the target relay protection device, the relay protection device number and addressing data corresponding to the number of the response code in the response code data are obtained, and the identification device is controlled to move to the target relay protection device according to the addressing data to re-obtain the identification image of the target relay protection device;
or according to the response code data not being the response code L and the response code R, after waiting time T, re-controlling the identification device to acquire the identification image of the target relay protection device;
the vertical correction sub-module is used for acquiring a vertical identification image of the target relay protection device according to the identification device after horizontal correction, and identifying the vertical identification image by using OpenCV to obtain vertical response code data;
according to the vertical response code data, namely a response code U and a response code D, and the numbers of the response code U and the response code D are consistent with the response code codes of the target relay protection device, completing the correction of the identification device;
or according to the vertical response code data as a response code U, the angle of an identification module in the identification device is downwards adjusted by 1 DEG until the response code D of the target relay protection device is identified;
Or according to the vertical response code data as the response code D, the angle of the identification module in the identification device is adjusted upwards by 1 degrees until the response code U of the target relay protection device is identified.
8. A terminal device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the intelligent identification method for the relay protection device according to any one of claims 1 to 5 according to the instructions in the program code.
CN202310518623.7A 2023-05-10 2023-05-10 Intelligent identification method, device and equipment for fixed inspection of relay protection device Active CN116231576B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310518623.7A CN116231576B (en) 2023-05-10 2023-05-10 Intelligent identification method, device and equipment for fixed inspection of relay protection device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310518623.7A CN116231576B (en) 2023-05-10 2023-05-10 Intelligent identification method, device and equipment for fixed inspection of relay protection device

Publications (2)

Publication Number Publication Date
CN116231576A CN116231576A (en) 2023-06-06
CN116231576B true CN116231576B (en) 2023-07-21

Family

ID=86573570

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310518623.7A Active CN116231576B (en) 2023-05-10 2023-05-10 Intelligent identification method, device and equipment for fixed inspection of relay protection device

Country Status (1)

Country Link
CN (1) CN116231576B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110109980A (en) * 2019-04-04 2019-08-09 广州供电局有限公司 Regular inspection material generation method, device, computer equipment and storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102692576A (en) * 2012-06-15 2012-09-26 黑龙江省电力有限公司检修公司 Relay protection periodical inspection method
JP5655172B1 (en) * 2014-10-03 2015-01-14 株式会社日立パワーソリューションズ Protection relay replacement support device and replacement support method thereof
CN111830342B (en) * 2020-07-04 2023-04-28 中国南方电网有限责任公司 Multi-system fusion intelligent substation relay protection dynamic fixed inspection method
CN111900694B (en) * 2020-07-07 2022-12-27 贵州电网有限责任公司 Relay protection equipment information acquisition method and system based on automatic identification
CN112014667A (en) * 2020-08-13 2020-12-01 贵州电网有限责任公司 Image information identification device and method for relay protection equipment
CN114037873A (en) * 2021-11-09 2022-02-11 国网山西省电力公司朔州供电公司 Transformer substation secondary circuit protection pressing plate detection system and method based on artificial intelligence

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110109980A (en) * 2019-04-04 2019-08-09 广州供电局有限公司 Regular inspection material generation method, device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN116231576A (en) 2023-06-06

Similar Documents

Publication Publication Date Title
CN111259892B (en) Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp
CN112734692B (en) Defect identification method and device for power transformation equipment
CN108537154B (en) Power transmission line bird nest identification method based on HOG characteristics and machine learning
CN111639647B (en) Indicator light state identification method and device, computer equipment and storage medium
CN114240939B (en) Method, system, equipment and medium for detecting appearance defects of mainboard components
CN112560816A (en) Equipment indicator lamp identification method and system based on YOLOv4
CN114119518A (en) Method and system for detecting temperature abnormal point in infrared image of current transformer
CN114693529B (en) Image splicing method, device and equipment and storage medium
CN113706455B (en) Rapid detection method for damage of 330kV cable porcelain insulator sleeve
CN116231576B (en) Intelligent identification method, device and equipment for fixed inspection of relay protection device
CN114549393A (en) Image annotation method, device, equipment and computer storage medium
CN116686535B (en) Unmanned harvester control method and system based on data analysis
CN117456358A (en) Method for detecting plant diseases and insect pests based on YOLOv5 neural network
CN115019297B (en) Real-time license plate detection and identification method and device based on color augmentation
CN108470141B (en) Statistical feature and machine learning-based insulator identification method in distribution line
CN116338392A (en) Method, device and equipment for identifying lightning discharge defects of glass insulator
CN113674341A (en) Robot visual identification and positioning method, intelligent terminal and storage medium
CN114354622A (en) Defect detection method, device, equipment and medium for display screen
CN113284103A (en) Substation equipment defect online detection system based on space transformation fast R-CNN model
Jiafeng et al. Image recognition and processing model of multi-circuit lines on the same tower based on artificial intelligence
CN112132898A (en) Photovoltaic module positioning method
CN114069844B (en) Substation secondary equipment state image recognition method based on deep learning
CN116310859B (en) Photovoltaic array fault intelligent detection method based on multi-source remote sensing data
Liao et al. A intelligent identification and judgment system for routine inspection of relay protection devices based on multiple fast response codes and multi-threaded binary search
CN115393273A (en) Power line inspection method and inspection platform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant