CN116012380A - Insulator defect detection method, device, equipment and medium - Google Patents
Insulator defect detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN116012380A CN116012380A CN202310301295.5A CN202310301295A CN116012380A CN 116012380 A CN116012380 A CN 116012380A CN 202310301295 A CN202310301295 A CN 202310301295A CN 116012380 A CN116012380 A CN 116012380A
- Authority
- CN
- China
- Prior art keywords
- insulator
- image
- images
- diameter
- acquired
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application discloses an insulator defect detection method, device, equipment and medium, wherein the method comprises the following steps: acquiring a first image of an insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a depression angle of the insulator; acquiring a plurality of second images of the insulator; the plurality of second images comprise images which are acquired at a second visual angle and rotate around the central axis by different angles, wherein the second visual angle is a front visual angle of the insulator; respectively carrying out image processing on the acquired first image and a plurality of second images; the characteristic information of the first image and the characteristic information of the plurality of second images after image processing are respectively extracted, and the characteristic information is compared with a database to obtain a comparison result; the database stores defect type data corresponding to the characteristics of the insulator; according to the comparison result, whether the insulator detected currently belongs to unqualified products is judged, and the insulator detection method has the advantages of being high in detection precision and high in detection efficiency.
Description
Technical Field
The present disclosure relates to the field of image data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for detecting an insulator defect.
Background
An insulator refers to a device that is mounted between conductors or conductors of different potential and a ground member and is capable of withstanding voltage and mechanical stress. The insulators are various in variety and different in shape, and the insulators of different types have large differences in structure and appearance, but are composed of two major parts, namely an insulating part and a connecting fitting.
The ceramic insulator or the glass insulator of a certain type is formed by bonding an insulating part (ceramic or glass material), an upper metal accessory and a lower metal accessory through adhesive, the insulating part is in a disc shape, a plurality of concentric circular ring bulges are arranged in the disc, defect detection is needed to be carried out on the insulator after manufacturing is finished so as to screen out unqualified products, and the insulator is mainly detected by means of purely manual visual inspection or by using an auxiliary measuring tool at present, and manual operation and calculation are needed by using the auxiliary measuring tool, so that the ceramic insulator or the glass insulator is troublesome in operation, low in detection efficiency, easy to have human errors in particular, and low in detection precision.
Disclosure of Invention
The main purpose of the application is to provide an insulator defect detection method, device, equipment and medium, and aims to solve the technical problem that the existing insulator defect detection method is low in detection precision.
In order to achieve the above object, the present application provides an insulator defect detection method, including the following steps:
acquiring a first image of an insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a depression angle of the insulator;
acquiring a plurality of second images of the insulator; the plurality of second images comprise images which are acquired at a second visual angle and rotate around the central axis by different angles, wherein the second visual angle is a front visual angle of the insulator;
respectively carrying out image processing on the acquired first image and a plurality of second images;
the characteristic information of the first image and the characteristic information of the plurality of second images after image processing are respectively extracted, and the characteristic information is compared with a database to obtain a comparison result; the database stores defect type data corresponding to the characteristics of the insulator;
and judging whether the insulator currently detected belongs to a defective product or not according to the comparison result.
Optionally, the image processing for the acquired first image and the plurality of second images respectively includes:
respectively carrying out gray processing on the acquired first image and the acquired plurality of second images so as to respectively acquire a first gray image and a plurality of second gray images;
noise reduction processing is carried out on the first gray level image and the plurality of second gray level images;
threshold segmentation is respectively carried out on the first gray level image and the plurality of second gray level images after noise reduction so as to respectively obtain a binarized image A and a plurality of binarized images B.
Optionally, the extracting feature information of the first image and the plurality of second images after image processing respectively, and comparing the feature information with a database to obtain a comparison result, includes:
extracting shadow information in the first gray level image and the plurality of second gray level images, comparing the shadow information with a database to detect whether abnormal shadow information exists, and stopping detection if the abnormal shadow information exists;
and extracting contour information of the binarized image A and the plurality of binarized images B, and comparing the contour information with a database to obtain a comparison result.
Optionally, the insulator comprises an insulating part, an upper metal accessory and a lower metal accessory which are respectively connected to the upper part and the lower part of the insulating part, and the insulating part is provided with a plurality of concentric circular ring bulges;
the extracting the outline information of the binarized image A and the plurality of binarized images B, and comparing the outline information with a database to obtain a comparison result, comprising:
respectively identifying annular contour information of each corresponding annular bulge in the binarized image A;
extracting a plurality of diameter data in each set of annular profile information to obtain a plurality of sets of diameter data sets { d1, d2, d3...dn }; the method comprises the steps that a plurality of diameter data are valued at the diameter sections corresponding to different positions of the annular contours, and n is the number of the diameter sections of each group of annular contours to be valued;
diameter maximum d in diameter dataset { d1, d2, d3...dn } is screened out max Diameter minimum d min If the diameter is maximum d max Not less than the upper limit value dΔ1 of the diameter or the minimum value d of the diameter min The diameter lower limit value dDelta2 is less than or equal to, and the comparison result is unqualified; wherein, the diameter upper limit value dDelta1 and the diameter lower limit value dDelta2 are preset values in a database;
obtaining an average diameter value dm of the diameter data sets { d1, d2 and d3...dn }, and if the average diameter value dm is more than or equal to a diameter standard value dDelta3, determining that the comparison result is unqualified; the diameter standard value dDelta3 is a preset value in a database.
Optionally, the extracting the profile information of the binarized image a and the plurality of binarized images B compares the profile information with a database to obtain a comparison result, and further includes:
respectively acquiring first contour information corresponding to an upper metal accessory and second contour information corresponding to a lower metal accessory in the binarized image B;
respectively constructing a standard central axis of the insulator, a first central axis of the first contour information and a second central axis of the second contour information corresponding to the binarized image B;
respectively acquiring an included angle theta 1 between the first central axis and the standard central axis, an included angle theta 2 between the second central axis and the standard central axis and an included angle theta 3 between the first central axis and the second central axis;
comparing the included angle theta 1 and the included angle theta 2 with a first threshold value theta m respectively, and if the included angle theta 1 or the included angle theta 2 is larger than or equal to the first threshold value theta m, determining that the comparison result is unqualified; the first threshold value thetam is the maximum error value preset in the database;
comparing the included angle theta 3 with a second threshold value theta n, and if the included angle theta 3 is larger than or equal to the second threshold value theta n, determining that the comparison result is unqualified; the second threshold value thetan is an error standard value preset in the database.
Optionally, the determining whether the currently detected insulator belongs to a defective product according to the comparison result includes:
obtaining a detection value (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) according to the average diameter value dm and the included angle theta 3; wherein, epsilon 1 and epsilon 2 are both conversion coefficients;
comparing the detection value (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) with a standard quality threshold epsilon, and judging that the insulator currently detected is a defective product if (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) > epsilon, otherwise, judging that the insulator is a defective product; the standard quality threshold epsilon is a qualified standard value preset in a database.
Optionally, the acquiring a plurality of second images of the insulator includes:
fixing the insulator on a rotating platform so as to enable the insulator to rotate for one circle;
a camera is adopted to collect video of the rotating insulator at the side part of the rotating platform;
the acquired video is processed to obtain a plurality of second images.
To achieve the above object, the present application further provides an insulator defect detection device, including:
the first image acquisition module is used for acquiring a first image of the insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a depression angle of the insulator;
the second image acquisition module is used for acquiring a plurality of second images of the insulator; the plurality of second images comprise images which are acquired at a second visual angle and rotate around the central axis by different angles, wherein the second visual angle is a front visual angle of the insulator;
the image processing module is used for respectively carrying out image processing on the acquired first image and the acquired plurality of second images;
the feature comparison module is used for respectively extracting the feature information of the first image and the plurality of second images after the image processing and comparing the feature information with a database to obtain a comparison result; the database stores defect type data corresponding to the characteristics of the insulator;
and the result judging module is used for judging whether the currently detected insulator belongs to a defective product or not according to the comparison result.
To achieve the above object, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the above method.
To achieve the above object, the present application further provides a computer readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the above method.
The beneficial effects that this application can realize are as follows:
because insulator structure specificity that this application needs to detect, need carry out defect detection to insulator top surface and side whole body, therefore this application can obtain the first image that the insulator top surface corresponds through the look-down angle, to the insulator side, through the rotatory different angles of front view acquisition insulator a plurality of second images, can obtain the image of insulator top surface and side whole body, utilize the machine vision recognition technology, can get rid of the error that the artificial interference caused, then handle first image and second image after, can carry out quantitative description to the characteristic information in first image and the second image, the testing result that has avoided the variation from person to person, detection grading error has been reduced, detection efficiency and detection precision have been improved, after extracting the characteristic information in first image and the second image, can compare with the database of predetermineeing, thereby obtain accurate testing result fast.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of an insulator defect detection method in an embodiment of the present application;
fig. 2 is a schematic structural diagram of an insulator according to an embodiment of the present application;
FIG. 3 is a schematic diagram of the top view of FIG. 2;
FIG. 4 is a schematic view of an included angle θ1 formed by a first central axis and a standard central axis in an embodiment of the disclosure;
FIG. 5 is a schematic view of an angle θ2 formed by the second central axis and the standard central axis in the embodiment of the application;
fig. 6 is a schematic diagram illustrating an included angle θ3 formed by the first central axis and the second central axis in an embodiment of the disclosure.
Reference numerals:
110-insulator, 111-annular boss, 120-upper metal accessory, 130-lower metal accessory.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present application are merely used to explain the relative positional relationship between the components, the movement condition, and the like in a specific posture, and if the specific posture is changed, the directional indicator is correspondingly changed.
In the present application, unless explicitly specified and limited otherwise, the terms "coupled," "secured," and the like are to be construed broadly, and for example, "secured" may be either permanently attached or removably attached, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and/or" as it appears throughout includes three parallel schemes, for example "A and/or B", including the A scheme, or the B scheme, or the scheme where A and B are satisfied simultaneously. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.
Example 1
Referring to fig. 1-6, the present embodiment provides an insulator defect detection method, which includes the following steps:
acquiring a first image of an insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a depression angle of the insulator;
acquiring a plurality of second images of the insulator; the plurality of second images comprise images which are acquired at a second visual angle and rotate around the central axis by different angles, wherein the second visual angle is a front visual angle of the insulator;
respectively carrying out image processing on the acquired first image and a plurality of second images;
the characteristic information of the first image and the characteristic information of the plurality of second images after image processing are respectively extracted, and the characteristic information is compared with a database to obtain a comparison result; the database stores defect type data corresponding to the characteristics of the insulator;
and judging whether the insulator currently detected belongs to a defective product or not according to the comparison result.
In this embodiment, the specificity of the insulator structure to be detected is that the whole body of the top surface and the side surface of the insulator is required to be detected, so that the first image corresponding to the top surface of the insulator can be obtained through the depression angle, the images of the whole body of the top surface and the side surface of the insulator can be obtained through collecting a plurality of second images of different angles of rotation of the insulator through the front view angle aiming at the side surface of the insulator, the errors caused by human interference can be eliminated by utilizing the machine vision recognition technology, then the first image and the second image are processed, the characteristic information in the first image and the second image can be quantitatively described, the detection result which varies with people is avoided, the detection grading error is reduced, the detection efficiency and the detection precision are improved, and the characteristic information in the first image and the second image can be compared with a preset database, so that the accurate detection result can be obtained quickly.
It should be noted that, the self-learning database is provided in the database, and the self-learning database may be used to store defect type data corresponding to unidentified insulator features, so that in the detection process, if defect information not existing in the database is detected, the defect type data corresponding to unidentified insulator features may be stored through a machine learning algorithm, so as to automatically perfect defect type data in the database, and identify more defect types.
As an optional implementation manner, the image processing for the acquired first image and the acquired plurality of second images respectively includes:
respectively carrying out gray processing on the acquired first image and the acquired plurality of second images so as to respectively acquire a first gray image and a plurality of second gray images;
noise reduction processing is carried out on the first gray level image and the plurality of second gray level images;
threshold segmentation is respectively carried out on the first gray level image and the plurality of second gray level images after noise reduction so as to respectively obtain a binarized image A and a plurality of binarized images B.
In this embodiment, when performing image processing, gray scale processing is first performed, it is advantageous to identify surface defects of a product according to a gray scale image, then noise reduction processing is performed on the gray scale image, so as to reduce noise in a digital image, so as to reduce image interference, and then threshold segmentation, that is, binarization processing is performed, so that a binary image a and a plurality of binary images B with distinct black and white are obtained, and extraction of relevant feature information is facilitated after the black and white image is formed.
The insulator in the present application comprises an insulator 110, an upper metal fitting 120 and a lower metal fitting 130 respectively connected to the upper and lower parts of the insulator 110, wherein the insulator 110 has a plurality of concentric circular protrusions 111; because the defects to be detected on the insulator product include surface defects of the product, whether the upper metal accessory 120 and the lower metal accessory 130 are in gluing position or not, and the like, wherein the surface defects include gaps, roundness of the circular ring bulge 111 and the like, and the circular ring bulge 111 has a certain deformation possibly caused by a process problem in the forming process, the circular ring bulge 111 is concave or convex, the roundness of the circular ring bulge 111 cannot meet the process requirement, and the gluing position refers to whether the upper metal accessory 120 and the lower metal accessory 130 are vertical after being glued on the upper part and the lower part of the insulator 110 or not, if not, the skew of the upper metal accessory 120 and the lower metal accessory 130 can meet the process requirement.
Therefore, as an optional implementation manner, the extracting the feature information of the first image and the plurality of second images after the image processing, and comparing the feature information with the database to obtain a comparison result includes:
extracting shadow information in the first gray level image and the plurality of second gray level images, comparing the shadow information with a database to detect whether abnormal shadow information exists, and stopping detection if the abnormal shadow information exists;
and extracting contour information of the binarized image A and the plurality of binarized images B, and comparing the contour information with a database to obtain a comparison result.
In this embodiment, by extracting the shadow information in the first gray scale image and the plurality of second gray scale images, and detecting whether abnormal shadow information exists, if so, it is indicated that a gap exists on the upper surface or the side surface of the insulator, if the substantial defect is detected, the defect is directly identified as a defective product, and further detection is not needed, so that the pressure of data processing is reduced.
As an optional implementation manner, the extracting the profile information of the binarized image a and the plurality of binarized images B, and comparing the profile information with a database to obtain a comparison result, includes:
respectively identifying annular contour information of each corresponding annular bulge 111 in the binarized image A;
extracting a plurality of diameter data in each set of annular profile information to obtain a plurality of sets of diameter data sets { d1, d2, d3...dn }; the method comprises the steps that a plurality of diameter data are valued at the diameter sections corresponding to different positions of the annular contours, and n is the number of the diameter sections of each group of annular contours to be valued;
diameter maximum d in diameter dataset { d1, d2, d3...dn } is screened out max Diameter minimum d min If the diameter is maximum d max Not less than the upper limit value dΔ1 of the diameter or the minimum value d of the diameter min The diameter lower limit value dDelta2 is less than or equal to, and the comparison result is unqualified; wherein, the diameter upper limit value dDelta1 and the diameter lower limit value dDelta2 are preset values in a database;
obtaining an average diameter value dm of the diameter data sets { d1, d2 and d3...dn }, and if the average diameter value dm is more than or equal to a diameter standard value dDelta3, determining that the comparison result is unqualified; the diameter standard value dDelta3 is a preset value in a database.
In this embodiment, when the roundness detection of the annular protrusions 111 is performed, the roundness of the annular profile information of all the annular protrusions 111 is detected from inside to outside or from outside to inside, and taking the inside to outside detection as an example, a plurality of diameter data in the innermost annular profile information are extracted first, that is, values are taken at the diameter sections corresponding to different positions (even intervals) of the annular profile, the number n of the diameter sections to be taken is set according to the detection precision and the process condition requirements, the larger the diameter is, the larger the number n of the diameter sections should be, and after obtaining the diameter data sets { d1, d2, d3...dn }, the diameter maximum d is selected out max Diameter minimum d min Maximum diameter d max Represents the maximum deformation of the annular protrusion 111 protruding outwards and the diameter minimum d min Representing the maximum deformation of the concave part of the annular protrusion 111, if the diameter is the maximum d max Not less than the upper limit value dΔ1 of the diameter or the minimum value d of the diameter min If the diameter lower limit value dDelta1 is less than or equal to, the outer convex deformation amount or the inner concave variable of the circular ring bulge 111 exceeds a preset value, and is proved to be unqualified, if both parameters meet the qualification standard, but when outer convex defects and inner concave defects exist simultaneously, although single detection meets the qualification standard, further detection is needed when both defects exist simultaneously according to the process requirement, so that an average diameter value dm is also introduced, the average diameter value dm= (d1+d2+d3+ & gt dn)/n is only introduced, and when the average diameter value dm is smaller than the diameter standard value dDelta3, the current annular profile information meets the qualification standard, the operation is repeated, and the residual annular profile information is sequentially detected and identified until all the annular profile information meets the standard, and the roundness of the circular ring bulge 111 meets the qualification standard. Therefore, the defect detection can be quantitatively described by adopting metering, the detection result is accurate and reliable, compared with the manual detection, the detection difficulty is high, the detection precision is low, and the defect detection method has higher practicability and reliability, thereby meeting higher detection requirements.
As an optional implementation manner, the extracting the profile information of the binarized image a and the plurality of binarized images B, and comparing the profile information with a database to obtain a comparison result, further includes:
respectively acquiring first contour information corresponding to the upper metal accessory 120 and second contour information corresponding to the lower metal accessory 130 in the binarized image B;
respectively constructing a standard central axis of the insulator, a first central axis of the first contour information and a second central axis of the second contour information corresponding to the binarized image B;
respectively acquiring an included angle theta 1 between the first central axis and the standard central axis, an included angle theta 2 between the second central axis and the standard central axis and an included angle theta 3 between the first central axis and the second central axis;
comparing the included angle theta 1 and the included angle theta 2 with a first threshold value theta m respectively, and if the included angle theta 1 or the included angle theta 2 is larger than or equal to the first threshold value theta m, determining that the comparison result is unqualified; the first threshold value thetam is the maximum error value preset in the database;
comparing the included angle theta 3 with a second threshold value theta n, and if the included angle theta 3 is larger than or equal to the second threshold value theta n, determining that the comparison result is unqualified; the second threshold value thetan is an error standard value preset in the database.
In this embodiment, in the case of performing the positive detection of the metal accessory, since the binarized image B is a plurality of images which are decomposed and processed from the video, two images corresponding to the upper metal accessory 120 and the lower metal accessory 130 with the largest deflection angle should be selected from the binarized image B, the first central axis (i.e., the axisymmetric line of the upper metal accessory 120) can be constructed according to the first profile information, and the second central axis (i.e., the axisymmetric line of the lower metal accessory 130) can be constructed according to the second profile information, so that the included angle θ1 between the first central axis and the standard central axis and the included angle θ2 between the second central axis and the standard central axis can be obtained, so that the deflection angles of the upper metal accessory 120 and the lower metal accessory 130 can be accurately obtained, and whether the deflection angles meet the requirements can be accurately determined by comparing with the first threshold θm. If both parameters meet the qualification standard, but considering that the relative deflection angle between the upper metal accessory 120 and the lower metal accessory 130 also affects the use or assembly performance of the insulator, an included angle theta 3 between the first central axis and the second central axis is also introduced, if both single detection meets the qualification standard, the included angle theta 3 is acquired again, and the included angle theta 3 is compared with the second threshold value thetan, wherein the first threshold value thetan and the second threshold value thetan are set according to the process requirement, and only after the included angle theta 1, the included angle theta 2 and the included angle theta 3 meet the qualification standard, the next step can be performed, and the detection result is accurate and reliable.
As an optional implementation manner, the determining whether the currently detected insulator belongs to a defective product according to the comparison result includes:
obtaining a detection value (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) according to the average diameter value dm and the included angle theta 3; wherein, epsilon 1 and epsilon 2 are both conversion coefficients;
comparing the detection value (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) with a standard quality threshold epsilon, and judging that the insulator currently detected is a defective product if (dm [ epsilon ] 1+theta 3 [ epsilon ] 2) > epsilon, otherwise, judging that the insulator is a defective product; the standard quality threshold epsilon is a qualified standard value preset in a database.
In this embodiment, according to the average diameter dm and the included angle θ3, a final detection value (dm×ε1+θ3×ε2) can be obtained, which is equivalent to that when the roundness of the annular protrusion 111 in the insulator and the deflection angles of the upper metal fitting 120 and the lower metal fitting 130 meet the conditions, the influence of the two defects on the overall quality of the insulator is considered, so that the final detection value (dm×ε1+θ3×ε2) is equivalent to the calculated overall quality parameter of the insulator, and the conversion coefficients ε1 and ε2 in the parameters are set according to the actual process conditions, so as to uniformly convert the diameter parameter and the included angle parameter into similar data, and when the detection value is less than or equal to ε, the current insulator is identified as a qualified product, otherwise, the current insulator is not qualified.
Therefore, the detection mode of evaluating the insulator defects locally and then integrally optimizes the detection sequence, reduces the data processing calculation amount, responds timely, can accurately and efficiently detect the parameters with high detection difficulty, and meets the current higher detection requirement.
As an alternative embodiment, the acquiring a plurality of second images of the insulator includes:
fixing the insulator on a rotating platform so as to enable the insulator to rotate for one circle;
a camera is adopted to collect video of the rotating insulator at the side part of the rotating platform;
the acquired video is processed to obtain a plurality of second images.
In this embodiment, the insulator should rotate at a slower speed when rotating for one revolution, so as to ensure the definition of the video, and thus ensure the definition of the image that is decomposed later, when processing the collected video, each frame of image is output from frame to frame, and after each frame of image is processed, a plurality of second images are obtained. Or in other embodiments, the insulator is stationary and revolves around the insulator at a constant speed for one revolution. The camera may be a CCD camera.
Example 2
Based on the same inventive concept as the foregoing embodiments, this embodiment further provides an insulator defect detection device, including:
the first image acquisition module is used for acquiring a first image of the insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a depression angle of the insulator;
the second image acquisition module is used for acquiring a plurality of second images of the insulator; the plurality of second images comprise images which are acquired at a second visual angle and rotate around the central axis by different angles, wherein the second visual angle is a front visual angle of the insulator;
the image processing module is used for respectively carrying out image processing on the acquired first image and the acquired plurality of second images;
the feature comparison module is used for respectively extracting the feature information of the first image and the plurality of second images after the image processing and comparing the feature information with a database to obtain a comparison result; the database stores defect type data corresponding to the characteristics of the insulator;
and the result judging module is used for judging whether the currently detected insulator belongs to a defective product or not according to the comparison result.
The explanation and examples of each module in the apparatus of this embodiment may refer to the method of the foregoing embodiment, and will not be repeated here.
Example 3
Based on the same inventive concept as the previous embodiments, the present embodiment further provides a computer device, where the computer device includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the above method.
Example 4
Based on the same inventive concept as the previous embodiments, this embodiment further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and a processor executes the computer program to implement the above method.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. The method for detecting the defects of the insulators is characterized by comprising the following steps:
acquiring a first image of an insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a overlook angle of the insulator;
acquiring a plurality of second images of the insulator; the plurality of second images comprise images acquired at a second visual angle, wherein the images are acquired at the second visual angle and rotate around the central axis by different angles, and the second visual angle is a front visual angle of the insulator;
respectively carrying out image processing on the acquired first image and the acquired plurality of second images;
respectively extracting characteristic information of the first image and the plurality of second images after image processing, and comparing the characteristic information with a database to obtain a comparison result; wherein, the database stores defect type data corresponding to the characteristics of the insulator;
and judging whether the insulator currently detected belongs to a defective product or not according to the comparison result.
2. The method for detecting an insulator defect according to claim 1, wherein the image processing of the acquired first image and the plurality of second images, respectively, comprises:
respectively carrying out gray processing on the acquired first image and the acquired plurality of second images so as to respectively acquire a first gray image and a plurality of second gray images;
noise reduction processing is carried out on the first gray level image and the plurality of second gray level images;
threshold segmentation is respectively carried out on the first gray level image and the plurality of second gray level images after noise reduction so as to respectively obtain a binarized image A and a plurality of binarized images B.
3. The method for detecting an insulator defect according to claim 2, wherein the steps of extracting the characteristic information of the first image and the plurality of second images after the image processing, respectively, and comparing the characteristic information with a database to obtain a comparison result, comprise:
extracting shadow information in the first gray level image and the plurality of second gray level images, comparing the shadow information with a database to detect whether abnormal shadow information exists, and stopping detection if abnormal shadow information exists;
and extracting contour information of the binarized image A and the plurality of binarized images B, and comparing the contour information with a database to obtain a comparison result.
4. A method of inspecting an insulator defect according to claim 3, wherein the insulator comprises an insulator member having a plurality of concentric annular protrusions thereon, and upper and lower metal fittings respectively connected to upper and lower portions of the insulator member;
the extracting the profile information of the binarized image A and the plurality of binarized images B, and comparing the profile information with a database to obtain a comparison result, including:
respectively identifying annular contour information of each corresponding annular bulge in the binarized image A;
extracting a plurality of diameter data in each set of the annular profile information to obtain a plurality of sets of diameter data sets { d1, d2, d3...dn }; the diameter data are valued at the diameter sections corresponding to different positions of the annular contour, and n is the number of the diameter sections of each group of annular contour to be valued;
screening the diameter data set { d1, d2, d3...dn } for a diameter maximum d } max Diameter minimum d min If the diameter is maximum d max Not less than the upper limit value dΔ1 of the diameter or the minimum value d of the diameter min The diameter lower limit value dDelta2 is less than or equal to, and the comparison result is unqualified; wherein the diameter upper limit value dΔ1 and the diameter lower limit value dΔ2 are preset values in the database;
obtaining an average diameter value dm of the diameter data sets { d1, d2 and d3...dn }, and if the average diameter value dm is more than or equal to a diameter standard value dDelta3, determining that the comparison result is unqualified; the diameter standard value dDelta3 is a preset value in a database.
5. The method for detecting an insulator defect according to claim 4, wherein the extracting contour information of the binarized image a and the plurality of binarized images B compares the contour information with a database to obtain a comparison result, further comprising:
respectively acquiring first contour information corresponding to the upper metal accessory and second contour information corresponding to the lower metal accessory in the binarized image B;
respectively constructing a standard central axis of the insulator, a first central axis of the first contour information and a second central axis of the second contour information corresponding to the binarized image B;
respectively acquiring an included angle theta 1 between the first central axis and the standard central axis, an included angle theta 2 between the second central axis and the standard central axis and an included angle theta 3 between the first central axis and the second central axis;
comparing the included angle theta 1 with the included angle theta 2 with a first threshold value theta m respectively, and if the included angle theta 1 or the included angle theta 2 is larger than or equal to the first threshold value theta m, determining that the comparison result is unqualified; wherein, the first threshold θm is a preset maximum error value in the database;
comparing the included angle theta 3 with the second threshold value thetan, and if the included angle theta 3 is larger than or equal to the second threshold value thetan, determining that the comparison result is unqualified; the second threshold value θn is an error standard value preset in the database.
6. The method for detecting defects of insulators according to claim 5, wherein said determining whether the insulator currently detected belongs to a defective product according to the comparison result comprises:
obtaining a detection value (dm [ epsilon ] 1+θ3 [ epsilon ] 2) according to the average diameter value dm and the included angle [ theta ] 3; wherein, epsilon 1 and epsilon 2 are both conversion coefficients;
comparing the detection value (dm [ epsilon ] 1+theta [ 3 ] epsilon 2) with a standard quality threshold epsilon, and judging that the insulator currently detected is a defective product if (dm [ epsilon ] 1+theta [ 3 ] epsilon 2) > epsilon, otherwise, judging that the insulator is a defective product; the standard quality threshold epsilon is a qualified standard value preset in the database.
7. The method for detecting defects of an insulator according to claim 1, wherein the step of obtaining a plurality of second images of the insulator comprises:
fixing the insulator on a rotating platform so as to enable the insulator to rotate for one circle;
a camera is adopted to collect video of the rotated insulator at the side part of the rotating platform;
and processing the acquired video to obtain a plurality of second images.
8. An insulator defect detection device, characterized by comprising:
the first image acquisition module is used for acquiring a first image of the insulator; the first image is an image of an insulator acquired at a first viewing angle, and the first viewing angle is a overlook angle of the insulator;
the second image acquisition module is used for acquiring a plurality of second images of the insulator; the plurality of second images comprise images acquired at a second visual angle, wherein the images are acquired at the second visual angle and rotate around the central axis by different angles, and the second visual angle is a front visual angle of the insulator;
the image processing module is used for respectively carrying out image processing on the acquired first image and the acquired plurality of second images;
the feature comparison module is used for respectively extracting the feature information of the first image and the plurality of second images after the image processing and comparing the feature information with a database to obtain a comparison result; wherein, the database stores defect type data corresponding to the characteristics of the insulator;
and the result judging module is used for judging whether the insulator currently detected belongs to a defective product or not according to the comparison result.
9. A computer device, characterized in that it comprises a memory in which a computer program is stored and a processor which executes the computer program, implementing the method according to any of claims 1-7.
10. A computer readable storage medium, having stored thereon a computer program, the computer program being executable by a processor to implement the method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310301295.5A CN116012380B (en) | 2023-03-27 | 2023-03-27 | Insulator defect detection method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310301295.5A CN116012380B (en) | 2023-03-27 | 2023-03-27 | Insulator defect detection method, device, equipment and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116012380A true CN116012380A (en) | 2023-04-25 |
CN116012380B CN116012380B (en) | 2023-06-16 |
Family
ID=86037750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310301295.5A Active CN116012380B (en) | 2023-03-27 | 2023-03-27 | Insulator defect detection method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116012380B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116797604A (en) * | 2023-08-28 | 2023-09-22 | 中江立江电子有限公司 | Glass insulator defect identification method, device, equipment and medium |
CN116863175A (en) * | 2023-08-31 | 2023-10-10 | 中江立江电子有限公司 | Right-angle connector defect identification method, device, equipment and medium |
CN117422718A (en) * | 2023-12-19 | 2024-01-19 | 中江立江电子有限公司 | Insulator performance evaluation method, device, equipment and medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001074437A (en) * | 1999-09-01 | 2001-03-23 | Hitachi Ltd | Device and method for inspecting circuit pattern |
JP2005164608A (en) * | 2005-01-07 | 2005-06-23 | Hitachi High-Technologies Corp | Pattern defect inspection method and device |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN106023185A (en) * | 2016-05-16 | 2016-10-12 | 国网河南省电力公司电力科学研究院 | Power transmission equipment fault diagnosis method |
CN106504247A (en) * | 2016-11-09 | 2017-03-15 | 广东电网有限责任公司电力科学研究院 | A kind of quick-fried automatic testing method of insulator chain based on visible images and device |
CN109870461A (en) * | 2019-03-29 | 2019-06-11 | 深圳市阿赛姆电子有限公司 | A kind of electronic component quality detection system |
CN110441310A (en) * | 2019-07-15 | 2019-11-12 | 中国科学院上海光学精密机械研究所 | Electronic component casing appearance defectoscopy device and measurement method |
CN111047561A (en) * | 2019-11-22 | 2020-04-21 | 国网江西省电力有限公司电力科学研究院 | Method for identifying cracks of shed tortoise of composite insulator |
CN111862013A (en) * | 2020-07-08 | 2020-10-30 | 湘潭大学 | Insulator detection method, device and equipment based on deep convolutional neural network |
CN114359286A (en) * | 2022-03-21 | 2022-04-15 | 湖南应超智能计算研究院有限责任公司 | Insulator defect identification method, device and medium based on artificial intelligence |
CN114399507A (en) * | 2022-03-25 | 2022-04-26 | 季华实验室 | Mobile phone appearance quality detection method and device, electronic equipment and storage medium |
CN114544674A (en) * | 2020-11-25 | 2022-05-27 | 国网河南省电力公司电力科学研究院 | Insulator flaw detection device and detection method |
CN115272199A (en) * | 2022-07-11 | 2022-11-01 | 成都数之联科技股份有限公司 | PCB carrier plate defect detection method and system, electronic equipment and medium |
CN115760820A (en) * | 2022-11-28 | 2023-03-07 | 湖北三江航天万峰科技发展有限公司 | Plastic part defect image identification method and application |
-
2023
- 2023-03-27 CN CN202310301295.5A patent/CN116012380B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001074437A (en) * | 1999-09-01 | 2001-03-23 | Hitachi Ltd | Device and method for inspecting circuit pattern |
JP2005164608A (en) * | 2005-01-07 | 2005-06-23 | Hitachi High-Technologies Corp | Pattern defect inspection method and device |
CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
CN106023185A (en) * | 2016-05-16 | 2016-10-12 | 国网河南省电力公司电力科学研究院 | Power transmission equipment fault diagnosis method |
CN106504247A (en) * | 2016-11-09 | 2017-03-15 | 广东电网有限责任公司电力科学研究院 | A kind of quick-fried automatic testing method of insulator chain based on visible images and device |
CN109870461A (en) * | 2019-03-29 | 2019-06-11 | 深圳市阿赛姆电子有限公司 | A kind of electronic component quality detection system |
CN110441310A (en) * | 2019-07-15 | 2019-11-12 | 中国科学院上海光学精密机械研究所 | Electronic component casing appearance defectoscopy device and measurement method |
CN111047561A (en) * | 2019-11-22 | 2020-04-21 | 国网江西省电力有限公司电力科学研究院 | Method for identifying cracks of shed tortoise of composite insulator |
CN111862013A (en) * | 2020-07-08 | 2020-10-30 | 湘潭大学 | Insulator detection method, device and equipment based on deep convolutional neural network |
CN114544674A (en) * | 2020-11-25 | 2022-05-27 | 国网河南省电力公司电力科学研究院 | Insulator flaw detection device and detection method |
CN114359286A (en) * | 2022-03-21 | 2022-04-15 | 湖南应超智能计算研究院有限责任公司 | Insulator defect identification method, device and medium based on artificial intelligence |
CN114399507A (en) * | 2022-03-25 | 2022-04-26 | 季华实验室 | Mobile phone appearance quality detection method and device, electronic equipment and storage medium |
CN115272199A (en) * | 2022-07-11 | 2022-11-01 | 成都数之联科技股份有限公司 | PCB carrier plate defect detection method and system, electronic equipment and medium |
CN115760820A (en) * | 2022-11-28 | 2023-03-07 | 湖北三江航天万峰科技发展有限公司 | Plastic part defect image identification method and application |
Non-Patent Citations (4)
Title |
---|
LEIYU NI 等: "Research on Insulator Defect Detection Method Based on Image Processing and Watershed Algorithm", 《AEERO》, pages 1 - 6 * |
TAOTAO ZHOU 等: "Mechanical defect detection of porcelain column high-voltage disconnector based on operating torque", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS》, pages 1 - 11 * |
王小雷: "玻璃绝缘子在线质量检测***研究与实现", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 2016, pages 042 - 28 * |
王昱晴 等: "玻璃绝缘子玻璃件缺陷的机器视觉检测方法", 《高压电技术》, vol. 48, no. 12, pages 1 - 8 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116797604A (en) * | 2023-08-28 | 2023-09-22 | 中江立江电子有限公司 | Glass insulator defect identification method, device, equipment and medium |
CN116797604B (en) * | 2023-08-28 | 2023-12-26 | 中江立江电子有限公司 | Glass insulator defect identification method, device, equipment and medium |
CN116863175A (en) * | 2023-08-31 | 2023-10-10 | 中江立江电子有限公司 | Right-angle connector defect identification method, device, equipment and medium |
CN116863175B (en) * | 2023-08-31 | 2023-12-26 | 中江立江电子有限公司 | Right-angle connector defect identification method, device, equipment and medium |
CN117422718A (en) * | 2023-12-19 | 2024-01-19 | 中江立江电子有限公司 | Insulator performance evaluation method, device, equipment and medium |
CN117422718B (en) * | 2023-12-19 | 2024-04-16 | 中江立江电子有限公司 | Insulator performance evaluation method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN116012380B (en) | 2023-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116012380B (en) | Insulator defect detection method, device, equipment and medium | |
CN113362326B (en) | Method and device for detecting defects of welding spots of battery | |
CN110047073B (en) | X-ray weld image defect grading method and system | |
TWI603074B (en) | Optical film defect detection method and system thereof | |
CN116109635B (en) | Method, device, equipment and medium for detecting surface quality of composite suspension insulator | |
CN115423813A (en) | Method for detecting welding defects on surface of welded pipe | |
JP5168215B2 (en) | Appearance inspection device | |
CN114943739A (en) | Aluminum pipe quality detection method | |
CN116721107B (en) | Intelligent monitoring system for cable production quality | |
CN110434090A (en) | A kind of carrot surface flaw detecting method | |
CN111398291A (en) | Flat enameled electromagnetic wire surface flaw detection method based on deep learning | |
CN116030053B (en) | Connector pin defect detection method, device, equipment and medium | |
CN115601369B (en) | Quality evaluation method for power transformation equipment support for power transmission and transformation engineering | |
CN115876823A (en) | Film defect detection method, film defect detection device and film defect detection system | |
CN116523922B (en) | Bearing surface defect identification method | |
CN116993725B (en) | Intelligent patch information processing system of flexible circuit board | |
CN117173177A (en) | Image-based metal shell optical size detection method and system | |
CN116205923B (en) | Nondestructive testing method for internal defects of automobile hub based on X-RAY | |
CN112541478A (en) | Insulator string stain detection method and system based on binocular camera | |
CN1287141C (en) | Method for detecting rolling products shape detect and reative device | |
CN115170476B (en) | Printed circuit board defect detection method based on image processing | |
JP2019194549A (en) | Inspection method for tire mold side plate | |
CN113222950A (en) | Surface defect detection model training method, surface defect detection method and system | |
CN111222495A (en) | Rolling bearing fault diagnosis method based on wavelet decomposition and improved Manhattan distance | |
CN115452845B (en) | LED screen surface damage detection method based on machine vision |
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 |