CN117115523A - Defect detection method and device, computer equipment, system and air conditioner - Google Patents
Defect detection method and device, computer equipment, system and air conditioner Download PDFInfo
- Publication number
- CN117115523A CN117115523A CN202311036166.4A CN202311036166A CN117115523A CN 117115523 A CN117115523 A CN 117115523A CN 202311036166 A CN202311036166 A CN 202311036166A CN 117115523 A CN117115523 A CN 117115523A
- Authority
- CN
- China
- Prior art keywords
- coordinate point
- point set
- horn mouth
- abnormal
- contour
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 70
- 230000007547 defect Effects 0.000 title claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 14
- 238000004519 manufacturing process Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 11
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 6
- 229910052802 copper Inorganic materials 0.000 description 6
- 239000010949 copper Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000004378 air conditioning Methods 0.000 description 3
- 238000005336 cracking Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009131 signaling function Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
Abstract
The application provides a defect detection method, a device, computer equipment, a system and an air conditioner, wherein the method comprises the steps of obtaining an image to be detected, and obtaining a contour coordinate point set of the outer edge of a horn mouth to be detected and circle center coordinates of an circumscribed circle of the horn mouth to be detected based on the image to be detected; calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinates; if the proportion of the abnormal coordinate points in the outline coordinate point set is smaller than a preset proportion threshold value, carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category; and if the number of the clustering categories is larger than a preset category threshold, judging that the horn mouth to be tested is unqualified. The method provided by the application can be used for rapidly detecting the horn mouths of the air conditioner evaporator and the condenser, and the accuracy and the reliability of the detection result are improved.
Description
Technical Field
The present application relates to the field of detection technologies, and in particular, to a defect detection method, device, computer equipment, system, and air conditioner.
Background
As basic components of an air-conditioning product, an air-conditioning evaporator and a condenser have important influences on the quality of the air-conditioning as a whole. In the production process of two parts of an air conditioner, the two parts after the expansion tube forming consist of fins, copper tubes and side plates, the side plates consist of cylindrical copper tubes and sheet metal parts, wherein the cylindrical copper tubes and the sheet metal parts extend out after penetrating through the fins, the opening of the copper tubes is a horn mouth, the opening part of the horn mouth is circular, and the quality, the size and the shape of the opening of the horn mouth have important influence on the quality of the subsequent copper tube opening welding process.
During the production process, part of the flare opening may have defects such as wrinkling, deformation, cracking or breakage. Traditional horn mouth defect detection mainly relies on production line personnel self-checking and inspector to carry out private inspection, and the mode of inspection mainly has first inspection and spot check, relies on the subjective judgement of people, and the mode based on diameter sample also has the hourglass to examine, and detection efficiency is low, wastes time and energy, and the testing result does not have quantization standard, problem such as reliability low is difficult to discern its cracking degree, also can't distinguish the circumstances such as slight flaw. And manual detection can not meet the automatic production requirement of intelligent factories.
The visual detection method based on the digital image processing technology mostly adopts a deep learning method to obtain a corresponding detection model in the aspect of horn mouth defect detection, and needs to provide massive original sample pictures for model training, so that the problems that sample data are difficult to collect in a short time, particularly, various defect sample pictures are difficult to collect in a large amount in a short time, the model training is long in time consumption and the like are solved; on the other hand, the detection result is obtained by only using the horn mouth picture to be detected to carry out visual processing, the processing method is relatively coarse, the standard of multi-factor comparison judgment is lacked, the detection result is easy to have the problems of misjudgment, misjudgment and the like, and the accuracy of the detection result is poor.
Disclosure of Invention
In order to solve the problem of low reliability of horn mouth defect detection of the existing air conditioner evaporator and condenser, the application provides a defect detection method, device, computer equipment, system and air conditioner, which can rapidly detect a horn mouth and improve the accuracy and reliability of detection results.
In one aspect, a defect detection method is provided, the method comprising:
acquiring an image to be measured, and acquiring a contour coordinate point set of the outer edge of the horn mouth to be measured and circle center coordinates of a circumscribed circle of the horn mouth to be measured based on the image to be measured;
calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinates;
if the proportion of the abnormal coordinate points in the outline coordinate point set is smaller than a preset proportion threshold value, carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category;
and if the number of the clustering categories is larger than a preset category threshold, judging that the horn mouth to be tested is unqualified.
In some embodiments, the method further comprises:
acquiring a radius standard value of an outer edge circumcircle of the standard horn mouth based on the historical image; the standard horn mouth is the same as the horn mouth to be measured in model
In some embodiments, the calculating the abnormal coordinate point set in the contour coordinate point set based on the radius standard value, the contour coordinate point set and the center coordinates includes:
calculating the distance between each contour coordinate point in the contour coordinate point set and the circle center coordinate;
and taking a contour coordinate point with the distance larger than a preset difference threshold value from the radius standard value as the abnormal coordinate.
In some embodiments, after calculating the abnormal coordinate point set in the contour coordinate point set based on the radius standard value, the contour coordinate point set and the center coordinates, the method further includes:
and if the proportion of the abnormal coordinate points in the contour coordinate point set is greater than or equal to a preset proportion threshold value, judging that the horn mouth to be tested is unqualified.
In some embodiments, after performing two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category, the method further includes:
if the number of the clustering categories is smaller than or equal to the category threshold value, calculating the stationarity value of the abnormal coordinate point of each clustering category;
if the stability value of the clustering class is larger than a preset stability threshold, judging that the horn mouth to be tested is unqualified;
the calculation formula of the stability threshold value comprises the following steps:
wherein S is ma N is the number of abnormal coordinate points in the class a clustering class, and (x, y) is the center coordinates, and (x) is the stability of the class a clustering class a,i ,y a,i ) R is the coordinate of the ith abnormal coordinate point in the class a cluster category m Is the radius standard value.
In another aspect, there is provided a defect detection apparatus, the apparatus comprising:
the image acquisition module is used for acquiring an image to be detected, and acquiring a contour coordinate point set of the outer edge of the horn mouth to be detected and circle center coordinates of a circumscribed circle of the horn mouth to be detected based on the image to be detected;
the coordinate calculation module is used for calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinate;
the clustering module is used for carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category if the proportion of the abnormal coordinate point to the contour coordinate point set is smaller than a preset proportion threshold value;
and the first judging module is used for judging that the horn mouth to be tested is unqualified if the number of the clustering categories is larger than a preset category threshold value.
In some embodiments, the apparatus further comprises a radius standard value acquisition module for:
acquiring a radius standard value of an outer edge circumcircle of the standard horn mouth based on the historical image; the standard horn mouth is the same as the horn mouth to be measured in model.
In some embodiments, the coordinate calculation module is specifically configured to:
calculating the distance between each contour coordinate point in the contour coordinate point set and the circle center coordinate;
and taking a contour coordinate point with the distance larger than a preset difference threshold value from the radius standard value as the abnormal coordinate.
In some embodiments, the apparatus further includes a second determining module configured to:
and if the proportion of the abnormal coordinate points in the contour coordinate point set is greater than or equal to a preset proportion threshold value, judging that the horn mouth to be tested is unqualified.
In some embodiments, the apparatus further includes a third determining module configured to:
if the number of the clustering categories is smaller than or equal to the category threshold value, calculating the stationarity value of the abnormal coordinate point of each clustering category;
if the stability value of the clustering class is larger than a preset stability threshold, judging that the horn mouth to be tested is unqualified;
the calculation formula of the stability threshold value comprises the following steps:
wherein S is ma N is the number of abnormal coordinate points in the class a clustering class, and (x, y) is the center coordinates, and (x) is the stability of the class a clustering class a,i ,y a,i ) R is the coordinate of the ith abnormal coordinate point in the class a cluster category m Is the radius standard value.
In another aspect, a computer device is provided, where the computer device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the processor may load and execute the at least one instruction, the at least one program, the code set, or the instruction set, to implement the defect detection method provided in the embodiment of the application.
In another aspect, a computer readable storage medium is provided, where at least one instruction, at least one program, a code set, or an instruction set is stored in the readable storage medium, and a processor may load and execute the at least one instruction, the at least one program, the code set, or the instruction set, so as to implement the defect detection method provided in the embodiment of the present application.
In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer program instructions stored in a computer readable storage medium. The processor reads the computer instructions from the computer-readable storage medium and executes the computer instructions to cause the computer device to perform the defect detection method as described in any of the above embodiments.
In another aspect, a defect detection system is provided comprising a computer device as described above with an image acquisition device.
In another aspect, there is provided an air conditioner including an evaporator and/or a condenser detected using the defect detection method as described above.
The technical scheme provided by the application has the beneficial effects that at least: the embodiment of the application provides a defect detection method, a device, computer equipment, a system and an air conditioner, wherein the method comprises the steps of obtaining an image to be detected, and obtaining a contour coordinate point set of the outer edge of a horn mouth to be detected and circle center coordinates of an circumscribed circle of the horn mouth to be detected based on the image to be detected; calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinates; if the proportion of the abnormal coordinate points in the outline coordinate point set is smaller than a preset proportion threshold value, carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category; and if the number of the clustering categories is larger than a preset category threshold, judging that the horn mouth to be tested is unqualified. The method provided by the embodiment of the application can be used for rapidly detecting the horn mouths of the air conditioner evaporator and the condenser, and the accuracy and the reliability of the detection result are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram showing an implementation flow of a defect detection method according to an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram showing a flare structure in a defect detection method according to an exemplary embodiment of the present application;
FIG. 3 is a diagram of a flare image in a defect detection method according to an exemplary embodiment of the present application;
FIG. 4 is a horn mouth diagram of a pass feature in a defect detection method according to an exemplary embodiment of the present application;
fig. 5 is a schematic structural diagram of a flare to be tested in a defect detection method according to an exemplary embodiment of the present application;
FIG. 6 is a flow chart illustrating yet another implementation of a defect detection method according to an exemplary embodiment of the present application;
FIG. 7 is a block diagram illustrating a defect detection apparatus according to an exemplary embodiment of the present application;
fig. 8 is a schematic structural diagram of a computer device corresponding to a defect detection method according to an exemplary embodiment of the present application;
fig. 9 is a schematic diagram of a detection system corresponding to a defect detection method according to an exemplary embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The defect detection method provided by the application can be used for rapidly detecting the horn mouth, and the accuracy and the reliability of the detection result are improved.
Embodiment 1,
Fig. 1 is a schematic implementation flow chart of a defect detection method according to an embodiment of the present application.
Referring to fig. 1, the defect detection method provided in the embodiment of the present application may include steps 101 to 104.
Fig. 2 shows a schematic diagram of a flare in the method according to the embodiment of the application.
Fig. 3 shows a schematic diagram of a flare image acquired in the method according to the embodiment of the present application. Optionally, preprocessing the original image to extract the horn mouth structure image.
Step 101: and acquiring an image to be detected, and acquiring a contour coordinate point set of the outer edge of the horn mouth to be detected and circle center coordinates of a circumscribing circle of the horn mouth to be detected based on the image to be detected.
Step 102: and calculating abnormal coordinate points in the contour coordinate point set based on the radius standard value, the contour coordinate point set and the circle center coordinates.
In some embodiments, the method prior to step 102 further comprises:
acquiring a radius standard value of an outer edge circumcircle of the standard horn mouth based on the historical image; the standard horn mouth is the same as the horn mouth to be measured in model.
In some embodiments, the normalized defect-free flare image is processed to obtain a minimum circumscribed circle radius value for the outer edge of the flare opening. And determining the radius standard value of the minimum circumscribed circle according to the radius values of the minimum circumscribed circles of a large number of standardized flawless horn mouth pictures.
Specifically, the two parts of the same type are produced by adopting copper pipes with the same specification, and each bell mouth is also formed by adopting the same technical standard. On the basis, a large number of two qualified device part bell mouth pictures of the same type are shot through a line scanning camera to be processed, a standardized bell mouth picture library is constructed, the standardized bell mouth picture is processed, and the minimum circumcircle radius of the outer edge of the opening is obtained according to the outline of the outer edge of the bell mouth. And determining the minimum circumcircle radius standard value of the horn mouth according to the average value of the minimum circumcircle radius of the horn mouth in the picture set.
Fig. 4 shows a flare schematic of a pass feature in a method according to an embodiment of the application.
Referring to fig. 4, a minimum circumscribed circle radius standard value of the flare is obtained based on a plurality of qualified flare images.
In a specific example, each horn mouth on two rows of 16-hole evaporator components is taken as a detection object, all horn mouths on each qualified component of the components are qualified horn mouths, and shooting environments, sizes and resolutions of all original pictures containing all horn mouths, which are shot by a line scan camera, are the same.
Optionally, in this embodiment, the upper left corner of the picture is taken as the origin of coordinates of the pixel domain, and the conversion metric value of the pixel and the actual physical size is 0.02106149115 (mm/pixel), which indicates that the real-time physical size corresponding to one pixel on the picture is 0.02106149115 mm.
Preprocessing an image, converting a horn mouth original image of a qualified part into a two-dimensional gray scale image, and then carrying out standardization processing on the original image through image processing operations such as horizontal overturning, rotation, low-pass filtering, median filtering, opening and closing operation, region cutting and the like to obtain N standardized horn mouth images to form an image library. And extracting a contour point set of the outer edge of each bell mouth opening according to each standardized bell mouth picture, and obtaining the radius value of the minimum circumcircle according to the contour point set.
In fig. 4, R1, R2, R3,..r32 represents a radius value of each bell mouth, and a radius standard value R of the bell mouth is calculated by the following formula m The radius standard value is the average value of all the bell mouth radius values on all the pictures:
wherein M is the total number of horn mouths on the pictures, and N is the total number of the pictures.
In some embodiments, the radius standard value of the flare may be directly set according to an actual production process standard, and the conversion between the pixel and the physical size is performed according to the conversion relationship between the pixel and the physical size.
In some embodiments, the image processing operations involved in the detection method may be performed under a physical size coordinate system according to the conversion relation of the pixels and the physical size.
Specifically, based on a horn mouth image of a device to be detected, which is obtained by a linear array camera, a contour coordinate point set of the outer edge of each horn mouth opening is obtained, and a circle center coordinate point of a corresponding minimum circumscribed circle is determined according to the contour point set.
In some embodiments, step 102 comprises:
calculating the distance between each contour coordinate point in the contour coordinate point set and the circle center coordinate;
and taking a contour coordinate point with the distance larger than a preset difference threshold value from the radius standard value as the abnormal coordinate.
In some embodiments, if the proportion of the abnormal coordinate points to the contour coordinate point set is greater than or equal to a preset proportion threshold, determining that the horn mouth to be tested is not qualified.
In some embodiments, a discrete set of contour coordinate points is obtained according to a preset step value, euclidean distance values between each coordinate point in the discrete set of contour coordinate points and a circle center coordinate point are calculated, and absolute values of differences between the distance values and radius standard values are calculated. And pre-judging the horn mouth to be detected according to the proportion value of the abnormal contour coordinate point.
Specifically, all the outer edge contour points meeting the step length value requirement are extracted according to a preset coordinate step length value and a circle center to form a discrete contour coordinate point set, the Euclidean distance value from the point to the circle center coordinate point is calculated for each contour coordinate point in the extracted discrete contour coordinate point set, the absolute value of the difference value between the distance value and the radius standard value is compared with a preset tolerance threshold value, when the absolute value is smaller than or equal to the preset tolerance threshold value, the contour point is considered to be on the minimum circumcircle, and when the absolute value is larger than the preset tolerance threshold value, the contour point is considered to be an abnormal contour point and not to be on the minimum circumcircle.
And extracting all the abnormal contour points to form a discrete abnormal contour coordinate point set.
Further, counting the number of abnormal contour coordinate points and the number of all contour coordinate points, calculating the ratio between the number of abnormal contour coordinate points and the number of all contour coordinate points, and when the ratio is larger than a preset threshold value, considering that the number of abnormal contour points of the flare opening on the minimum circumscribing circle is too large, directly judging that the flare opening is an unqualified flare opening, otherwise, carrying out the next processing judgment.
Fig. 5 shows a schematic diagram of a flare to be measured in the method according to the embodiment of the application.
Referring to fig. 5, in some embodiments, all sets of contour coordinate points of the outer edge of the bell mouth on the bell mouth picture to be detected are acquired, and the circle center coordinate point (x, y) corresponding to the minimum circumscribed circle is determined according to the contour of the sets.
In some embodiments, the coordinates of the center point of the smallest circumcircle of the outline can be determined according to all outline points of the outline or some key points such as corner points.
In some embodiments, the coordinates of the center point of the smallest circumscribed circle of all straight wall contour points or the key points of the contour, such as the corner points, can be determined.
In a specific example, preprocessing an acquired horn mouth picture to be detected, extracting a contour coordinate point set of the outer edge of an opening of the horn mouth picture, determining a circle center coordinate point (x, y) of a corresponding minimum circumcircle according to the extracted contour point set, assuming that a preset x-axis coordinate step value s=2, taking the circle center coordinate point (x, y) as a reference point, extracting all x-axis coordinate values as [ x-Ns ], the terms, x-3s, x-2s, x-s, x, x+s, x+2s, x+3s, the terms, x+ms]Form a discrete contour coordinate point set, calculate the Euclidean distance between each discrete contour coordinate point and the circle center point, and assume that the coordinates of a certain discrete contour point are (x) i ,y i ) The distance between the center point and the center point is d i The method comprises the following steps:
calculating the absolute value of the difference between the distance value and the radius standard value Rm:
d e ＝|d i -R m |
will d e Discrete contour coordinate points greater than a preset tolerance threshold T are defined as abnormal discrete contour coordinate points, and then the ratio P between the number of abnormal contour coordinate points and the number of all contour coordinate points is calculated, and when the ratio is greater than a preset threshold, P is calculated t And if the horn mouth is not qualified, ending the detection, otherwise, performing the next processing judgment.
Step 103: and if the proportion of the abnormal coordinate points in the outline coordinate point set is smaller than a preset proportion threshold value, carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category.
Step 104: and if the number of the clustering categories is larger than a preset category threshold, judging that the horn mouth to be tested is unqualified.
If the number of the clustering categories is smaller than or equal to the category threshold value, calculating the stationarity value of the abnormal coordinate point of each clustering category;
if the stability value of the clustering class is larger than a preset stability threshold, judging that the horn mouth to be tested is unqualified;
the calculation formula of the stability threshold value comprises the following steps:
wherein S is ma N is the number of abnormal coordinate points in the class a clustering class, and (x, y) is the center coordinates, and (x) is the stability of the class a clustering class a,i ,y a,i ) R is the coordinate of the ith abnormal coordinate point in the class a cluster category m Is the radius standard value.
In some embodiments, clustering is performed on the pre-qualified horn mouth to be detected, a discrete coordinate point set is subjected to clustering, for various abnormal contour point sets, a stability value of a distance value between a contour point and a circle center is calculated, the stability value is compared with a preset stability threshold value to judge whether the contour point set meets requirements, and finally whether the horn mouth to be detected is qualified is determined according to the classified class number and the stability judging result.
Wherein the stationarity value is the arithmetic square root of the average of the sum of the squares of the differences between each distance value and the radius standard value.
Specifically, the discrete abnormal contour coordinate point sets are subjected to clustering classification processing, are divided into a plurality of discrete abnormal contour coordinate point subsets, and for each type of abnormal contour coordinate point set, the arithmetic square root value of the average of the sum of the squares of the differences of the distance values between the contour points and the circle centers and the radius standard values is calculated, and the value is defined as the stability value representing the contour.
In some embodiments, when the number of classified objects obtained after classification is greater than a preset threshold, the edge of the flare opening is considered to have an excessive local defect area, and the flare opening is directly judged to be an unqualified flare without considering the specific situation of the defect; when the number of classification meets the requirement, if the stability value of a certain class is larger than a preset threshold value, the local area of the edge of the horn mouth opening is considered to have defects, the horn mouth opening is judged to be an unqualified horn mouth, and otherwise, the horn mouth opening is considered to be a qualified horn mouth.
In a specific example, two-dimensional clustering is performed on the abnormal contour coordinate point set, for example, the abnormal discrete coordinate point set is divided into four categories a, b, c and d, when the number of categories is greater than a preset upper limit threshold value L, the flare is considered to be unqualified, otherwise, the stability value Sm of the data points of each abnormal contour coordinate point set is calculated.
According to the defect detection method provided by the embodiment of the application, whether the contour points are abnormal points or not is judged through the approach degree of the distance value between each outer edge contour point and the circle center of the horn mouth picture to be detected and the radius value of the standard circumscribing circle, and whether the horn mouth to be detected is qualified or not is judged according to the occupation ratio of the abnormal points or the classified category number and the quantized discrete degree value of various abnormal contour point sets. The method can comprehensively consider various deformation defect problems of the horn mouth opening caused by wrinkling, cracking or breaking, so that the horn mouth can be rapidly detected, and the accuracy and the reliability of the detection result are improved.
Embodiment II,
Fig. 6 is a schematic flow chart of another implementation of the defect detection method according to the embodiment of the present application.
Referring to fig. 6, in a specific example, the implementation procedure of the method provided by the embodiment of the present application is as follows.
Firstly, processing a standardized horn mouth picture, and determining a radius standard value of a minimum circumcircle of the horn mouth.
And extracting all contour coordinate points of the outer edge of each horn mouth to be detected on the horn mouth picture to be detected, and determining the circle center coordinate point of the minimum circumscribed circle of the horn mouth according to the contour.
And obtaining a discrete contour coordinate point set according to a preset coordinate step value, calculating an absolute value of a difference value between the Euclidean distance from the contour coordinate point to the circle center and a radius standard value, and comparing the absolute value with a preset tolerance threshold value to obtain an abnormal contour coordinate point set.
Judging whether the horn mouth is qualified or not according to the proportion of the abnormal contour coordinate points, and outputting a detection result if the horn mouth is qualified.
If the coordinates are not qualified, clustering the discrete coordinate point sets, calculating the stability value of various coordinates, and comparing the stability value with a preset stability value for judgment.
And determining whether the horn mouth to be detected is qualified or not according to the classified class number and the stability judging result, if not, repairing and rechecking the horn mouth, and if so, outputting a detection result.
In summary, the defect detection method provided by the embodiment of the application can be used for rapidly detecting the horn mouth, and the accuracy and the reliability of the detection result are improved.
Third embodiment,
Fig. 7 is a schematic structural diagram of a defect detecting device according to an embodiment of the present application.
Referring to fig. 7, a defect detecting apparatus provided in an embodiment of the present application includes:
the image acquisition module 201 is configured to acquire an image to be measured, and acquire a contour coordinate point set of an outer edge of a horn mouth to be measured and a circle center coordinate of a circumscribed circle of the horn mouth to be measured based on the image to be measured;
a coordinate calculation module 202, configured to calculate an abnormal coordinate point in the contour coordinate point set based on a radius standard value, the contour coordinate point set, and the center coordinates;
the clustering module 203 is configured to perform two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering class if the proportion of the abnormal coordinate point to the contour coordinate point set is less than a preset proportion threshold;
the first determining module 204 is configured to determine that the horn mouth to be tested is not qualified if the number of the cluster categories is greater than a preset category threshold.
In some embodiments, the apparatus further comprises a radius standard value acquisition module for:
acquiring a radius standard value of an outer edge circumcircle of the standard horn mouth based on the historical image; the standard horn mouth is the same as the horn mouth to be measured in model.
In some embodiments, the coordinate calculation module is specifically configured to:
calculating the distance between each contour coordinate point in the contour coordinate point set and the circle center coordinate;
and taking a contour coordinate point with the distance larger than a preset difference threshold value from the radius standard value as the abnormal coordinate.
In some embodiments, the apparatus further includes a second determining module configured to:
and if the proportion of the abnormal coordinate points in the contour coordinate point set is greater than or equal to a preset proportion threshold value, judging that the horn mouth to be tested is unqualified.
In some embodiments, the apparatus further includes a third determining module configured to:
if the number of the clustering categories is smaller than or equal to the category threshold value, calculating the stationarity value of the abnormal coordinate point of each clustering category;
if the stability value of the clustering class is larger than a preset stability threshold, judging that the horn mouth to be tested is unqualified;
the calculation formula of the stability threshold value comprises the following steps:
wherein S is ma N is the number of abnormal coordinate points in the class a clustering class, and (x, y) is the center coordinates, and (x) is the stability of the class a clustering class a,i ,y a,i ) R is the coordinate of the ith abnormal coordinate point in the class a cluster category m Is the radius standard value.
In summary, the device provided by the embodiment of the application can rapidly detect the horn mouth, and the accuracy and the reliability of the detection result are improved.
Fourth embodiment,
Fig. 8 shows a schematic structural diagram of a computer device according to an exemplary embodiment of the present application, where the computer device includes:
processor 301, including one or more processing cores, executes various functional applications and data processing by running software programs and modules by processor 301.
The receiver 302 and the transmitter 303 may be implemented as one communication component, which may be a communication chip. Alternatively, the communication component may be implemented to include a signaling function. That is, the transmitter 303 may be used to transmit control signals to the image acquisition device and the scanning device, and the receiver 302 may be used to receive corresponding feedback instructions.
The memory 304 is connected to the processor 301 by a bus 305.
The memory 304 may be used for storing at least one instruction, and the processor 301 is configured to execute the at least one instruction to implement steps 101 to 102 in the above-described method embodiment.
It will be appreciated by those skilled in the art that fig. 8 is merely an example of a computer device and is not limiting of a computer device, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the computer device may also include a network access device, etc.
The processor 301 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 304 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The memory 304 may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like. Further, the memory 304 may also include both internal storage units and external storage devices of the computer device. The memory 304 is used for storing the computer program and other programs and data required by the terminal device. The memory 304 may also be used to temporarily store data that has been output or is to be output.
Fifth embodiment (V),
The embodiment of the application also provides a defect detection system which comprises the image acquisition equipment and the computer equipment.
Fig. 9 shows a schematic structural diagram of an inspection system to which the method according to the embodiment of the present application is applied.
Referring to fig. 9, the production line PLC master control apparatus is connected to the industrial personal computer and the production line of the two-device component side plate bell mouth, respectively. The 8K line scanning camera shoots an image of the horn mouth of the side plate, the image is sent to the industrial personal computer, the industrial personal computer performs image processing and detection, and the detection result is sent to the display terminal for display.
Optionally, the industrial personal computer is in communication connection with the production line PLC main control equipment through a MODBUS communication protocol, and the production line PLC main control equipment controls the running state of each working procedure position of the production line. When the two parts reach the defect detection station through the production line conveyor belt, the conveyor belt stops running, and the two parts are in a static state.
The 8K line scanning camera positioned right in front of the side plate with the horn mouth of the two parts is used for capturing pictures of the horn mouth of the two parts of the side plate in a scanning shooting mode according to a control instruction of the industrial personal computer, and the pictures are stored on the industrial personal computer.
The industrial personal computer detects the defects of the shot bell mouth picture by the defect detection method provided by the application through detection software, and sends the detection result to the PLC main control equipment of the production line. The display terminal can display the horn mouth detection result in real time.
And the production line PLC main control equipment controls the flowing direction of the current two parts on the conveyor belt according to the detection result, flows all the parts with qualified bell mouth detection results to the next production process position, and flows the parts with unqualified bell mouth detection results to the unqualified repairing area for the next repairing and rechecking.
Embodiment six,
The embodiment of the application also provides an air conditioner which comprises the evaporator and/or the condenser detected by the defect detection method. .
Embodiment seven,
The embodiment of the application also provides a computer readable storage medium, wherein at least one instruction, at least one section of program, code set or instruction set is stored in the readable storage medium, so as to be loaded and executed by a processor to realize the defect detection method.
Alternatively, the computer-readable storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), solid state disk (SSD, solid State Drives), or optical disk, etc. The random access memory may include resistive random access memory (ReRAM, resistance Random Access Memory) and dynamic random access memory (DRAM, dynamic Random Access Memory), among others.
Example eight,
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method of any of the above embodiments.
The foregoing description of the embodiments of the present application is provided for the purpose of illustration only, and does not represent the advantages or disadvantages of the implementation.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, where the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc. It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A method of defect detection, the method comprising:
acquiring an image to be measured, and acquiring a contour coordinate point set of the outer edge of the horn mouth to be measured and circle center coordinates of a circumscribed circle of the horn mouth to be measured based on the image to be measured;
calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinates;
if the proportion of the abnormal coordinate points in the outline coordinate point set is smaller than a preset proportion threshold value, carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category;
and if the number of the clustering categories is larger than a preset category threshold, judging that the horn mouth to be tested is unqualified.
2. The method according to claim 1, wherein the method further comprises:
acquiring a radius standard value of an outer edge circumcircle of the standard horn mouth based on the historical image; the standard horn mouth is the same as the horn mouth to be measured in model.
3. The method of claim 1, wherein the calculating the abnormal coordinate point in the set of contour coordinate points based on the radius criterion value, the set of contour coordinate points, and the center coordinates comprises:
calculating the distance between each contour coordinate point in the contour coordinate point set and the circle center coordinate;
and taking a contour coordinate point with the distance larger than a preset difference threshold value from the radius standard value as the abnormal coordinate.
4. A method according to claim 3, wherein after calculating the abnormal coordinate point set in the contour coordinate point set based on the radius standard value, the contour coordinate point set, and the center coordinates, the method further comprises:
and if the proportion of the abnormal coordinate points in the contour coordinate point set is greater than or equal to a preset proportion threshold value, judging that the horn mouth to be tested is unqualified.
5. The method according to any one of claims 1 to 4, wherein after performing two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one cluster category, the method further comprises:
if the number of the clustering categories is smaller than or equal to the category threshold value, calculating the stationarity value of the abnormal coordinate point of each clustering category;
if the stability value of the clustering class is larger than a preset stability threshold, judging that the horn mouth to be tested is unqualified;
the calculation formula of the stability threshold value comprises the following steps:
wherein S is ma N is the number of abnormal coordinate points in the class a clustering class, and (x, y) is the center coordinates, and (x) is the stability of the class a clustering class a,i ,y a,i ) R is the coordinate of the ith abnormal coordinate point in the class a cluster category m Is the radius standard value.
6. A defect detection apparatus, the apparatus comprising:
the image acquisition module is used for acquiring an image to be detected, and acquiring a contour coordinate point set of the outer edge of the horn mouth to be detected and circle center coordinates of a circumscribed circle of the horn mouth to be detected based on the image to be detected;
the coordinate calculation module is used for calculating abnormal coordinate points in the contour coordinate point set based on a radius standard value, the contour coordinate point set and the circle center coordinate;
the clustering module is used for carrying out two-dimensional clustering calculation on the abnormal coordinate point set to obtain at least one clustering category if the proportion of the abnormal coordinate point to the contour coordinate point set is smaller than a preset proportion threshold value;
and the first judging module is used for judging that the horn mouth to be tested is unqualified if the number of the clustering categories is larger than a preset category threshold value.
7. A computer device comprising a processor and a memory having stored therein at least one instruction, at least one program, code set, or instruction set that is loaded and executed by the processor to implement the defect detection method of any of claims 1 to 5.
8. A defect detection system comprising an image acquisition device and a computer device as claimed in claim 7.
9. An air conditioner comprising an evaporator and/or a condenser detected by the defect detection method according to any one of claims 1 to 5.
10. A computer readable storage medium having stored therein at least one instruction, at least one program, code set, or instruction set that is loaded and executed by a processor to implement the defect detection method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311036166.4A CN117115523A (en) | 2023-08-16 | 2023-08-16 | Defect detection method and device, computer equipment, system and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311036166.4A CN117115523A (en) | 2023-08-16 | 2023-08-16 | Defect detection method and device, computer equipment, system and air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115523A true CN117115523A (en) | 2023-11-24 |
Family
ID=88808447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311036166.4A Pending CN117115523A (en) | 2023-08-16 | 2023-08-16 | Defect detection method and device, computer equipment, system and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115523A (en) |
-
2023
- 2023-08-16 CN CN202311036166.4A patent/CN117115523A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251333B (en) | Element reverse detection method and system | |
| CN111223078B (en) | Method for determining flaw level and storage medium | |
| CN109544533A (en) | A kind of metal plate defect detection and measure based on deep learning | |
| CN109741295B (en) | Product quality detection method and device | |
| CN116109635B (en) | Method, device, equipment and medium for detecting surface quality of composite suspension insulator | |
| CN117571721B (en) | Method and device for detecting surface defects of circuit board bonding pad and storage medium | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| Chavan et al. | Quality control of PCB using image processing | |
| CN117455917B (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
| CN113554645B (en) | Industrial anomaly detection method and device based on WGAN | |
| CN114677348A (en) | IC chip defect detection method and system based on vision and storage medium | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN117522778A (en) | Hollow brick flaw detection system | |
| CN116993725A (en) | Intelligent patch information processing system of flexible circuit board | |
| CN114596243A (en) | Defect detection method, device, equipment and computer readable storage medium | |
| CN115170476B (en) | Printed circuit board defect detection method based on image processing | |
| CN117115523A (en) | Defect detection method and device, computer equipment, system and air conditioner | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model | |
| CN113870754B (en) | Method and system for judging defects of panel detection electronic signals | |
| CN110634124A (en) | Method and equipment for area detection | |
| CN107123105A (en) | Images match defect inspection method based on FAST algorithms | |
| CN111539933B (en) | Direct-insert element detection method and system | |
| CN111524097B (en) | Method and device for detecting horn mouth of two devices, storage medium and equipment |
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 |