CN110119680B - Automatic error checking system of regulator cubicle wiring based on image recognition - Google Patents
Automatic error checking system of regulator cubicle wiring based on image recognition Download PDFInfo
- Publication number
- CN110119680B CN110119680B CN201910266990.6A CN201910266990A CN110119680B CN 110119680 B CN110119680 B CN 110119680B CN 201910266990 A CN201910266990 A CN 201910266990A CN 110119680 B CN110119680 B CN 110119680B
- Authority
- CN
- China
- Prior art keywords
- image
- wiring
- electrical
- camera
- electrical cabinet
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/66—Testing of connections, e.g. of plugs or non-disconnectable joints
- G01R31/67—Testing the correctness of wire connections in electric apparatus or circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an automatic wiring error checking system of an electrical cabinet based on image recognition, which comprises an industrial personal computer, a camera, an image monitoring display screen, an operation maintenance display screen and a state indicating and control switch, wherein the camera is used for displaying images; the industrial personal computer is respectively connected with the camera, the image monitoring display screen, the operation and maintenance display screen and the state indication and control switch; the camera acquires an electrical wiring image on the front surface of the electrical cabinet and sends the electrical wiring image to the industrial personal computer, the industrial personal computer positions the image, identifies the wire number on the terminal position, compares the wire number with a standard wiring database to determine whether the wire number on the terminal position is consistent, the consistency is correct, and the inconsistency is wrong. Compared with the prior art, the invention has the advantages of quick and accurate inspection of wiring of the electrical cabinet under the condition of not contacting the tested wire.
Description
Technical Field
The invention relates to an automatic error checking system for electrical cabinet wiring, in particular to an automatic error checking system for electrical cabinet wiring based on image recognition.
Background
With the rapid development of the economy in China, the urban electricity consumption is rapidly increased, and meanwhile, a large amount of investment of a power distribution cabinet is driven, the power distribution cabinet distributes and controls electric equipment, and power-off protection is provided when overload, short circuit and electric leakage occur to a circuit. The correct wiring of the electrical cabinet is thus a necessary measure to ensure safe operation.
The existing electric wiring has different wiring rules and requirements due to different types, properties and levels of signals. However, at present, problems still exist, such as too crowded of cabinet design layout, and rapid inspection after wiring is difficult; the arrangement of components is unreasonable, which is not beneficial to wiring; the strong and weak electric wiring is mixed and staggered; no good grounding measures are taken; insufficient heat dissipation space between the driving and power devices is a safety hazard. And is not beneficial to the engineering personnel to quickly and effectively carry out equipment maintenance.
The inspection of regulator cubicle wiring mainly relies on staff's people's eye discernment, colour calibration, position inspection etc. just look like the heart when facing complicated regulator cubicle, and the degree of accuracy is not high enough, causes the potential safety hazard easily.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an automatic wiring error checking system of an electrical cabinet based on image recognition, and in the checking process of electrical wiring, the wiring of the electrical cabinet is checked rapidly and accurately under the condition of not contacting with the tested wire so as to meet the requirements of safe work of personnel and equipment.
The aim of the invention can be achieved by the following technical scheme:
an automatic error checking system for electrical cabinet wiring based on image recognition comprises an industrial personal computer, a camera, an image monitoring display screen, an operation maintenance display screen, a state indication and control switch; the industrial personal computer is respectively connected with the camera, the image monitoring display screen, the operation and maintenance display screen and the state indication and control switch;
the camera acquires an electrical wiring image on the front surface of the electrical cabinet and sends the electrical wiring image to the industrial personal computer, the industrial personal computer positions the image, measures the position of the wiring terminal, recognizes the wire number on the position, compares the position with a standard wiring database to determine whether the position of the terminal and the wire number on the position are consistent, the consistency is correct, and the inconsistency is wrong.
Preferably, the industrial personal computer comprises an image recognition and detection unit, wherein the image recognition and detection unit obtains picture information by photographing a camera at a fixed distance position on the front surface of the electrical cabinet, obtains the position and the line number of the wiring through image recognition, and determines whether the wiring is accurate or not by comparing the position and the line number with a standard wiring database for making the wiring when the electrical cabinet is designed.
Preferably, after the industrial personal computer acquires the image of the electric cabinet, carrying out Gaussian filtering, correction and binarization pretreatment of a dynamic threshold value on the image;
establishing an image characteristic model of the terminal and the number tube, detecting and identifying the edges of a plurality of wiring terminals in the image according to the characteristic model, dividing the edges into independent terminal areas, and numbering the areas;
and then the terminal is subjected to image detection of the position and the line number, the position is calculated from the area range, and the line number is determined by calibrating the position and the direction of characters on the wire number tube and then performing character recognition.
Preferably, the numbering sequence is from left to right and from top to bottom.
Preferably, the standard wiring database data generating method comprises the following steps:
manually inputting the position and the line number of each line one by one;
or the EPLAN or other electrical diagram design software is used for completing the wiring table of the electrical diagram and converting the wiring table to generate a wiring database.
Preferably, the standard wiring database is an SQL database, and the database is a local or server.
Preferably, the camera is a high-resolution camera, the display content of the operation and maintenance display screen comprises the selection of the type of the electric cabinet, and the display content of the image monitoring display screen comprises images collected by the camera, inspection information and error checking results of all wiring in the electric cabinet.
Preferably, after the automatic identification and detection of the electrical cabinet by the industrial personal computer is completed, the detection result is analyzed according to the wiring list, the problems of missing detection, error detection and terminal failure in the detection process are found, and the secondary identification is carried out through the appointed position of the problem.
Preferably, for producing electrical cabinets of various types, the standard wiring database establishes a plurality of standard wiring data tables, each data table corresponds to a type of electrical cabinet, the produced electrical cabinet type is selected on the operation and maintenance display screen, and the electrical cabinet type is connected to the corresponding wiring data table.
Preferably, the image recognition and detection unit is used for receiving the digital image transmitted by the camera, preprocessing the image, recognizing the model of the power distribution cabinet and the terminal numbers at all positions, inputting the digital image into a data table to be detected containing the positions and the terminal numbers, quickly searching the corresponding table in the SQL database through the recognized model of the power distribution cabinet, comparing and detecting the terminal numbers at all positions, if all the terminal numbers are the same, indicating that the wiring is correct, and returning the result to the electric wiring detection result output unit; if the difference occurs, the wiring is wrong, the wrong terminal number is returned to the electric wiring detection result output unit, and one-time complete detection is completed.
Compared with the prior art, the invention has the following advantages:
(1) The camera is adopted to acquire wiring data to be detected in a photographing mode, the application range is wide, the operation is easy, the influence of external environment factors is small, and the requirement on the surrounding environment of an object to be detected is low.
(2) The detection result is displayed on the LCD display screen, can be directly read, does not need to be manually checked, and has high working efficiency. And the detection result is obtained based on automatic processing of machine vision, and the accuracy is higher.
(3) When complex line inspection is carried out, the operation method is simple and convenient, non-contact detection is adopted, and the safety is high.
(4) The device has small volume, is easy to carry, is suitable for complex working environments, is beneficial to popularization in markets, and promotes the development of the field of machine vision detection.
Drawings
FIG. 1 is a schematic diagram of a hardware architecture of the present invention;
FIG. 2 is a schematic diagram of the working principle of the present invention;
FIG. 3 is an automated cross-flow chart of the present invention;
FIG. 4 is a schematic view of an image before binarization;
fig. 5 is a schematic diagram of the image after binarization processing.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
As shown in fig. 2, the camera is used to obtain an electrical wiring image on the front of the electrical cabinet, the image is positioned, the wire number on the terminal position is identified, and the wire number on the terminal position is compared with a standard wiring database to determine whether the wire number on the terminal position is consistent, the consistency is correct, and the inconsistency is wrong.
The electric connection image acquisition unit is realized by photographing the fixed distance and position of the front face of the electric cabinet by the camera, and the photographed image is transmitted to the image recognition detection unit.
The recognition wiring is a line at a certain terminal position, the position is position data of the terminal calculated by the reference position of the image, and the character of the line at the position is recognized.
The position and the wire number of the wiring are obtained through image recognition and are compared with a standard wiring database for making the wiring when the electrical cabinet is designed, so that whether the wiring is accurate or not is determined.
After the image of the electrical cabinet is acquired, the image is subjected to gaussian filtering, correction and binarization pretreatment of dynamic threshold values (as shown in fig. 4 and 5). Because a plurality of connecting terminals are arranged in the electric cabinet, an image characteristic model of the terminals and the number tubes is established, edges of a plurality of connecting terminals in an image are detected and identified according to the characteristic model, the connecting terminals are divided into independent terminal areas, the areas are numbered, and the numbers are from left to right and from top to bottom. And then the terminal is subjected to image detection of the position and the line number, the position can be calculated from the area range, and the line number is determined by calibrating the position and the direction of characters on the wire number tube and then performing character recognition.
The data generation method of the standard wiring database has several manual input positions and line numbers for each line one by one; and converting the wiring table of the electrical diagram by EPLAN or other electrical diagram design software to generate a wiring database. The wiring database is an SQL database, which can be a local or server
As shown in FIG. 1, the system comprises a high-resolution camera connected to an industrial personal computer, the industrial personal computer is connected with an image monitoring display screen, an operation maintenance display screen, a state indication and control switch, and the display content of an LCD screen comprises the type selection of an electrical cabinet, images acquired by the camera, inspection information and error checking results of all wiring in the electrical cabinet.
After the automatic identification and detection of the electrical cabinet are finished, analyzing the detection result according to the wiring list, finding out the problems of missing detection, error detection and terminal failure in the detection process, and carrying out secondary identification through the appointed position of the problem.
For producing multiple models of electrical cabinets, the database may establish a plurality of standard wiring tables, each table corresponding to a model of an electrical cabinet. The model of the electrical cabinet produced is selected on the screen and is connected to the corresponding wiring meter, so that the product model of the production line is convenient and quick to replace.
As shown in fig. 3, the image recognition and detection unit is configured to receive a digital image transmitted from the camera, preprocess the image, recognize the model number of the power distribution cabinet and the terminal numbers at each position, and input the digital image and the terminal numbers into a data table to be detected including the positions and the terminal numbers. The corresponding form is quickly searched in the SQL database through the identified power distribution cabinet model, then the terminal numbers at all positions are compared and detected, if all the terminal numbers are the same, the correct wiring is indicated, and the result is returned to the electric wiring detection result output unit; if the difference occurs, the wiring is wrong, the wrong terminal number is returned to the electric wiring detection result output unit, and one-time complete detection is completed.
The invention mainly relates to a non-contact checking mode for detecting whether the wiring of a power distribution cabinet is correct by applying a machine vision method. Especially in some special occasions, when the detected electrical cabinet cannot be accessed for inspection, an image is obtained through photographing, whether wiring is correct or not is detected by using an image recognition algorithm, and convenience, rapidness and high efficiency of electric wiring detection are facilitated for engineering personnel.
The principle of the invention is that a camera is used for aligning a measured object, an LCD display screen displays an acquired object image in real time, a touch screen is used for adjusting the size and the position of a measured wire in the display image, after a key is determined, a microcomputer acquires image data shot by the camera, and separation, binarization, classification, data filtering and machine identification calculation of the image data are carried out to obtain position data of the wire in a specified electrical cabinet and number data on the wire; and comparing the test result with the correct wiring patterns prestored in the memory, and displaying the test result on the LCD screen. If the problem exists, a warning prompt is sent out to remind the engineering personnel to check again. Checking for errors indicates "correct" on the screen.
The camera is used for image acquisition and information transmission of wiring in the electric cabinet, and the singlechip is connected with the microcomputer and then carries out corresponding data processing and analysis on the acquired image information.
The key module is used as an input part of man-machine interaction, and when photographing operation is performed, after the image acquired by the camera meets the requirement, a user can perform picture stop-motion through keys. After photographing is finished, other operations such as calling the image and selecting the wiring area to be tested in the image can be performed through keys.
The detailed process of the invention is as follows:
aiming at the problems that the conventional electrical cabinet detection method is complex and has low detection efficiency, the machine vision is used for replacing the manual vision, the wiring condition is detected by adopting a machine identification method, a database is established, and the automatic error detection is carried out on the electrical wiring.
Three positioning points with the same size are set up on the electric cabinet as reference positions before photographing, and a rectangular coordinate system is established according to the positions of the positioning points after image acquisition. Point O, A, B is the anchor point, assuming point O is the origin of coordinates;the direction of the point O pointing to the point A is the x-axis direction, and the straight line is the x-axis; the direction in which the point O points to the point B is the y-axis direction, and the straight line is the y-axis. The actual lengths of the line segments OA, OB are known and are denoted as l, respectively i 、l j The position coordinates of all the connection points are thus fixed. Scales are marked on the x axis and the y axis uniformly according to the actual size, so that a rectangular coordinate system on the electric cabinet is established. And (3) sequentially and respectively detecting the distances between each cable wiring point and the abscissa and the ordinate by taking the scale on the coordinate axis as a standard, so that the cable wiring position information can be obtained. The detection point is recorded as point P, perpendicular lines are respectively drawn from the point P to the x-axis and the y-axis, respectively intersected at point M and point N, and the lengths of line segments OA and OB in the image are respectively x l 、y l The lengths of the line segments OM and ON in the image are x respectively p 、y p The actual distances x and y from the point P to the coordinate axis are respectively
I.e. the position information of the point P is
After the position information is acquired, the line number is identified according to the cable image information of the detection point. The invention aims at solving the defects of the traditional edge extraction operator in filtering and threshold selection, and the computer is used for carrying out image preprocessing on the acquired wiring diagram of the electrical cabinet to be detected, and extracting the edge information of the wiring diagram for detecting the cable number. The characteristic of components smaller than structural elements in an image can be eliminated by utilizing corrosion operation, the adhesion among characters to be detected and the influence of small particle noise are eliminated, and a template method is adopted to identify the number of the cable after the character string is segmented.
The template contains the serial numbers and the coordinates of the wiring points of each cable in the electrical cabinet, so that a complete database is required to be established, and a wiring table is required to be acquired, which is difficult to realize by using the conventional electrical design software AutoCAD. By using the EPLAN to design an electrical schematic diagram, data among the modules can be shared, the design is more efficient and standard, and the wiring is more accurate and reasonable. After wiring is completed, setting corresponding parameters in the tag, deriving connection data, and storing the wiring table into a MySQL database to form a complete database as a template.
The serial number information and the position information of the cable are compared with corresponding data in the template as a detection result, and result information is output. If the detection result is the same as the data in the database or within the error allowable range, the wiring is correct, and the result is returned to the electric wiring detection result output unit; if the difference is out of the error allowable range, the wiring is wrong, and the wrong cable number is output.
Machine identification of wires
Image preprocessing
In detecting the serial number information of the cable, the extraction of the image edge contour is important. Currently, common edge detection operators include Canny operators, roberts operators, sobel operators, and the like. The invention improves the defects of the traditional Canny operator in filtering denoising and threshold selection, replaces Gaussian filtering by adopting a mode of combining self-adaptive smooth filtering and morphological closing operation, and selects a threshold by adopting a maximum inter-class variance method (Otsu), thereby improving the edge detection precision.
(1) Filter improvement
The simple smoothing filtering can remove noise and lose part of original image details at the same time, so that the image is blurred, and the adaptive smoothing filtering is adopted, so that detail parts can be increased while denoising is performed, and the image enhancement effect is improved. The basic principle of adaptive smoothing filtering is to perform iterative convolution with the original image a fixed number of times with a template of adaptive weights. Let the original image be f (i, j), then the gradient components after the kth iteration are respectively
The template coefficient of the filter is
For f (k) (i, j) weighted averaging
The parameter k needs to be set before the iteration starts.
After the self-adaptive smoothing filter processing is carried out on the image, the edge of the image is not smooth, small holes caused by misjudgment are distributed in the object area, and the image is subjected to the closed operation processing, so that the edge of the image can be smoothed in the range with small area change of the object, and tiny holes can be eliminated to connect broken parts of edge lines. The filtering mode of performing the closed operation after the self-adaptive smoothing filtering of the image can effectively remove noise, sharpen edge contours and smooth region edges.
(2) Adaptive threshold
The traditional Canny operator needs to manually set a threshold value, partial edge information can be lost when the threshold value is too high, some pseudo edges can be generated when the threshold value is too low, the edge continuity can be seriously affected when the threshold value is unreasonably set, adaptability is poor, and efficiency is low. In order to obtain a more reasonable threshold and improve detection accuracy, the method adopts a maximum inter-class variance method (Otsu) to adaptively select the threshold.
The basic principle of the Otsu method is to divide the image pixels into a background part and a foreground part according to the gray characteristic of the image, so that the separation between classes is the best, namely, the threshold with the largest inter-class variance is the best threshold.
Assume that an image of size M N pixels contains L different gray levels, denoted by {0,1,2, …, L-1}The number of pixels with gray level i is n i Then
MN＝n 0 +n 1 +…+n L-1 (7)
The probability of gray i is
p i ＝n i /MN (8)
Selecting threshold k (k is more than 0 and less than L-1), dividing the image into C 1 = {0,1, …, k } and C 2 Two parts = { k+1, k+2, …, L-1}, then the pixel is classified into C 1 And C 2 The probabilities of (a) are respectively
Assigned to C 1 And C 2 The pixel average gray value of (a) is
Accumulated mean value of k
Global mean value of
The inter-class variance is availableIs that
When the variance is maximum, the optimal threshold k=k is noted * I.e.
The optimal threshold k obtained by Otsu method * As a high threshold for Canny operator, by T h ＝2T l The criteria of (2) may be low threshold, thus adaptively selecting the high and low thresholds of the Canny operator. The method replaces the method of manually setting the threshold value in the traditional Canny operator, is simple and convenient to calculate, is not easily influenced by the contrast of the image, and has ideal effect.
And detecting the image edge by adopting the improved Canny operator, wherein the result is superior to the traditional Canny operator.
Wire number identification
The number of the cables is more and the arrangement is crowded, and after the original image is preprocessed, the obtained edge outline of the character to be detected still has a slight adhesion phenomenon, so that the image needs to be further processed in order to finish the detection of the number of the cables. The erosion operation may shrink the image, eliminating components in the image that are smaller than the structural elements. The corrosion operation is applied to the image detected by the improved Canny operator, so that the image can be thinned, the adhesion between characters to be detected and the influence of small particle noise can be effectively eliminated, and characters with relatively close distances can be separated.
The cable number is a string of characters, character segmentation is needed to complete character recognition, and an image is segmented into a series of single character images. The method comprises the steps of firstly carrying out progressive scanning on an image from top to bottom to mark the approximate height range of the character, and then carrying out progressive scanning from left to right in the height range to mark the approximate width range of the character. And continuously scanning the whole character string according to the method, carrying out preliminary judgment on the range of each character, and carrying out fine adjustment on the height and the width of the character by combining a priori knowledge method to obtain the final frame of character segmentation.
The invention adopts the template matching method to identify the characters, and the cable serial number character string is simpler and is usually only composed of a plurality of English characters and numbers, so that a complete database can be established as a template. After the character images are normalized to be 64 multiplied by 64 in uniform size, the character images to be recognized are compared with the character templates, so that the similarity between the character images is obtained, and the final detection result is the highest similarity.
The invention provides a method for automatically detecting errors of an electric connection established by combining image processing and a database. The filtering denoising and threshold selection of the traditional Canny operator are improved, so that the accuracy of image edge contour extraction is effectively improved. And after the serial number and the position information of the cable are acquired, comparing the serial number and the position information with template data, and outputting a detection result. The detection method can effectively improve the accuracy and efficiency of error detection, and can be applied to the fields of production and manufacture of electrical cabinets and error detection of electrical wiring.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The automatic wiring error checking system for the electrical cabinet based on image recognition is characterized by comprising an industrial personal computer, a camera, an image monitoring display screen, an operation maintenance display screen and a state indicating and control switch; the industrial personal computer is respectively connected with the camera, the image monitoring display screen, the operation and maintenance display screen and the state indication and control switch;
the camera acquires an electrical wiring image on the front surface of the electrical cabinet and sends the electrical wiring image to the industrial personal computer, the industrial personal computer positions the image, measures the position of the wiring terminal and identifies the wire number on the position, and compares the position with a standard wiring database to determine whether the position of the terminal and the wire number on the position are consistent, the consistency is correct, and the inconsistency is wrong;
the industrial personal computer comprises an image recognition and detection unit, wherein the image recognition and detection unit obtains picture information by photographing a camera at a fixed distance position on the front surface of the electrical cabinet, obtains the position and the wire number of a wire through image recognition, and compares the position and the wire number with a standard wire database for making wires when the electrical cabinet is designed to determine whether the wires are correct or not;
the image recognition detection unit is used for receiving the digital image transmitted by the camera, preprocessing the image, recognizing the model of the power distribution cabinet and the terminal numbers at all positions, inputting the digital image into a data table to be detected containing the positions and the terminal numbers, quickly searching the corresponding table in the SQL database through the recognized model of the power distribution cabinet, comparing and detecting the terminal numbers at all positions, if all the terminal numbers are the same, indicating that the wiring is correct, and returning the result to the electric wiring detection result output unit; if the difference occurs, the wiring is wrong, the wrong terminal number is returned to the electric wiring detection result output unit, and one-time complete detection is completed;
after the industrial personal computer acquires the image of the electrical cabinet, carrying out Gaussian filtering, correction and binarization pretreatment of a dynamic threshold value on the image;
establishing an image characteristic model of the terminal and the number tube, detecting and identifying the edges of a plurality of wiring terminals in the image according to the characteristic model, dividing the edges into independent terminal areas, and numbering the areas;
then, the terminal is subjected to image detection of the position and the line number, the position is calculated from the area range, and the line number is determined by calibrating the position and the direction of characters on the wire number tube and then performing character recognition;
adopting a mode of combining self-adaptive smoothing filtering and morphological closing operation to replace Gaussian filtering, and selecting a threshold value by using a maximum inter-class variance method; the adaptive smoothing filtering is adopted, the detail part is added while denoising is performed, and the image enhancement effect is improved; applying corrosion operation to the image detected by the improved Canny operator to refine the image; the characters are segmented by a method combining a projection method and a priori knowledge method.
2. The automatic wiring error checking system for electrical cabinets based on image recognition according to claim 1, wherein the numbering sequence is from left to right and from top to bottom.
3. The automatic wiring error checking system for electrical cabinets based on image recognition according to claim 1, wherein the standard wiring database data generating method comprises the steps of:
manually inputting the position and the line number of each line one by one;
or the EPLAN or other electrical diagram design software is used for completing the wiring table of the electrical diagram and converting the wiring table to generate a wiring database.
4. An automatic wiring error checking system for electrical cabinets based on image recognition according to claim 3, wherein the standard wiring database is an SQL database, which is a local or server.
5. The automatic wiring error checking system for the electrical cabinet based on image recognition according to claim 1, wherein the camera is a high-resolution camera, the display content of the operation maintenance display screen comprises electrical cabinet model selection, and the display content of the image monitoring display screen comprises images acquired by the camera, inspection information and error checking results of all wiring in the electrical cabinet.
6. The automatic wiring error checking system for the electrical cabinet based on image recognition according to claim 1, wherein after the automatic recognition and detection of the electrical cabinet by the industrial personal computer are completed, the detection result is analyzed according to a wiring list, the problems of missing detection, error checking and terminal failing to be found in the detection process are found, and the secondary recognition is carried out through the appointed position of the problem.
7. The automatic wiring error checking system for electrical cabinets based on image recognition according to claim 1, wherein for producing electrical cabinets of various types, the standard wiring database establishes a plurality of standard wiring data tables, each corresponding to a type of electrical cabinet, and selects a type of electrical cabinet to be produced on the operation and maintenance display screen and connects to the corresponding wiring data table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910266990.6A CN110119680B (en) | 2019-04-03 | 2019-04-03 | Automatic error checking system of regulator cubicle wiring based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910266990.6A CN110119680B (en) | 2019-04-03 | 2019-04-03 | Automatic error checking system of regulator cubicle wiring based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110119680A CN110119680A (en) | 2019-08-13 |
| CN110119680B true CN110119680B (en) | 2023-08-01 |
Family
ID=67520779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910266990.6A Active CN110119680B (en) | 2019-04-03 | 2019-04-03 | Automatic error checking system of regulator cubicle wiring based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110119680B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110943373B (en) * | 2019-11-25 | 2020-12-04 | 珠海格力电器股份有限公司 | Wiring arrangement method and device for electric cabinet and computer readable storage medium |
| CN110895249A (en) * | 2019-11-26 | 2020-03-20 | 广州供电局有限公司 | Cable joint identification system and method |
| CN111312023B (en) * | 2020-03-20 | 2022-02-08 | 上海中科教育装备集团有限公司 | Device and method for automatically drawing middle school physics circuit experiment circuit diagram |
| CN111242135A (en) * | 2020-03-23 | 2020-06-05 | 贵州电网有限责任公司 | Automatic wiring diagram generation equipment for transformer substation secondary screen cabinet and operation method thereof |
| CN112001238A (en) * | 2020-07-14 | 2020-11-27 | 浙江大华技术股份有限公司 | Terminal block wiring state recognition method, recognition device, and storage medium |
| CN111832946A (en) * | 2020-07-15 | 2020-10-27 | 国家电网有限公司技术学院分公司 | Wiring technology quantitative scoring system and method based on machine vision |
| CN112526182A (en) * | 2020-11-18 | 2021-03-19 | 广东电网有限责任公司 | Ammeter wiring appurtenance |
| CN112396025A (en) * | 2020-12-01 | 2021-02-23 | 浙江三一装备有限公司 | Checking system and checking method for electric circuit |
| CN112668620A (en) * | 2020-12-22 | 2021-04-16 | 湖南世优电气股份有限公司 | Machine vision identification method and device and readable storage medium |
| CN114842494B (en) * | 2021-12-23 | 2024-04-05 | 华南理工大学 | Method for automatically identifying connection relation of power system station wiring diagrams |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4040222A1 (en) * | 1990-12-15 | 1992-06-17 | Ind Rheinboellen Gmbh | Path control for object handling robots - is carried out by flexible program based on analysis of optical data |
| CN109117764A (en) * | 2018-07-29 | 2019-01-01 | 国网上海市电力公司 | Using the method for color threshold method identification target object region electrical symbol in power monitoring |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5382533B2 (en) * | 2009-02-19 | 2014-01-08 | 株式会社ひたちなかテクノセンター | Cable connection check system and identification tag manufacturing method |
| US8407155B2 (en) * | 2009-12-11 | 2013-03-26 | Pitney Bowes Inc. | On-line mail processing system and mobile device application therefor |
| US20140301645A1 (en) * | 2013-04-03 | 2014-10-09 | Nokia Corporation | Method and apparatus for mapping a point of interest based on user-captured images |
| US9626564B2 (en) * | 2014-11-17 | 2017-04-18 | Intel Corporation | System for enabling eye contact in electronic images |
| FR3056966B1 (en) * | 2016-10-04 | 2018-10-05 | Safran Electrical & Power | METHOD OF LOCATING DEFECT IN ELECTRICAL HARNESSES |
| US10061996B1 (en) * | 2017-10-09 | 2018-08-28 | Hampen Technology Corporation Limited | Face recognition method and system for personal identification and authentication |
| CN109271844B (en) * | 2018-07-29 | 2023-03-28 | 国网上海市电力公司 | Electrical cabinet electrical symbol recognition method based on OpenCV |
| CN109409395A (en) * | 2018-07-29 | 2019-03-01 | 国网上海市电力公司 | Using the method for template matching method identification target object region electrical symbol in power monitoring |
-
2019
- 2019-04-03 CN CN201910266990.6A patent/CN110119680B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4040222A1 (en) * | 1990-12-15 | 1992-06-17 | Ind Rheinboellen Gmbh | Path control for object handling robots - is carried out by flexible program based on analysis of optical data |
| CN109117764A (en) * | 2018-07-29 | 2019-01-01 | 国网上海市电力公司 | Using the method for color threshold method identification target object region electrical symbol in power monitoring |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power |
Non-Patent Citations (2)
| Title |
|---|
| 基于图像识别和遗传算法的Tripod机器人最优轨迹控制;李尧;石红瑞;;计算机应用(第S1期);全文 * |
| 基于机器视觉的零件产品检测***设计;顾桂鹏;邵勇;张钰婷;昝鹏;;工业控制计算机(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110119680A (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119680B (en) | Automatic error checking system of regulator cubicle wiring based on image recognition | |
| CN105957059B (en) | Electronic component missing part detection method and system | |
| CN111693534B (en) | Surface defect detection method, model training method, device, equipment and medium | |
| CN106529559A (en) | Pointer-type circular multi-dashboard real-time reading identification method | |
| CN109271844B (en) | Electrical cabinet electrical symbol recognition method based on OpenCV | |
| CN108520514B (en) | Consistency detection method for electronic elements of printed circuit board based on computer vision | |
| CN109993154B (en) | Intelligent identification method for single-pointer sulfur hexafluoride instrument of transformer substation | |
| CN106845545B (en) | Image recognition method and device in automatic digital electric meter calibration device | |
| CN108955901B (en) | Infrared temperature measurement method and system and terminal equipment | |
| CN113030123B (en) | AOI detection feedback system based on Internet of things | |
| CN111553176B (en) | Wireless transmission checking method and system suitable for wiring of substation screen cabinet | |
| CN112132781A (en) | Texture defect detection method and device | |
| CN111223078B (en) | Method for determining flaw level and storage medium | |
| CN116309518A (en) | PCB (printed circuit board) detection method and system based on computer vision | |
| CN115471476A (en) | Method, device, equipment and medium for detecting component defects | |
| CN113269234B (en) | Connecting piece assembly detection method and system based on target detection | |
| CN113705350A (en) | Pointer instrument reading identification method and device for transformer substation, medium and electronic equipment | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN108898584A (en) | A kind of full-automatic veneering capacitor welding equipment polarity discriminating method based on image analysis | |
| CN107533748A (en) | Component kind automatic distinguishing method, component kind automatic discrimination system, image procossing generate system with component data generation method and image procossing component data | |
| CN114155380A (en) | Instrument panel image identification method and device, computer equipment and storage medium | |
| CN107389677B (en) | Method and device for detecting quality of flannelette fluff | |
| CN110909735A (en) | Intelligent electric energy meter chip visual identification comparison system and method based on convolutional neural network | |
| Zou et al. | A method for positioning mark point on liquid crystal glass based on machine vision | |
| CN117726239B (en) | Engineering quality acceptance actual measurement method and system |
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 |