CN115294134A - Valve sealing surface defect identification method - Google Patents
Valve sealing surface defect identification method Download PDFInfo
- Publication number
- CN115294134A CN115294134A CN202211225419.8A CN202211225419A CN115294134A CN 115294134 A CN115294134 A CN 115294134A CN 202211225419 A CN202211225419 A CN 202211225419A CN 115294134 A CN115294134 A CN 115294134A
- Authority
- CN
- China
- Prior art keywords
- crack
- region
- pixel points
- possibility
- ring
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Gasket Seals (AREA)
Abstract
The invention relates to the technical field of data identification, in particular to a method for identifying defects of a valve sealing surface, which comprises the following steps: identifying and acquiring a wound gasket image, segmenting the image to obtain an inner ring area and an outer ring area, calculating the gray level uniformity degree of the areas, and acquiring the image of which the gray level uniformity degree is greater than a threshold value; setting a window with a fixed size to perform sliding window processing on the wound gasket image, and traversing the pixel points according to the central deviation values of the pixel points to obtain a crack area; obtaining a possible defect area according to pixel points in the crack defect area, and calculating the cracking possibility; when the cracking possibility is smaller than a threshold value, calculating the possibility of cracks in the crack area according to the gradient of the pixel points in the crack area; and judging the defects of the valve sealing gasket according to the possibility of the cracks in the crack area and the possibility threshold. The invention avoids the problem that the defects of the filling layer cannot be identified accurately or even cannot be identified conventionally, and improves the accuracy of the identification efficiency.
Description
Technical Field
The invention relates to the technical field of data identification, in particular to a method for identifying defects of a valve sealing surface.
Background
The flange gasket is used for the gasket of the joint of the pipeline flange or the valve flange, and the flange is metal, so that the flange and the flange are not tightly engaged, the gasket is added between the two flanges, the gasket plays a role in sealing, the sealing performance of the valve is ensured, and the outward leakage of the joint of the valve is avoided. Some valves need to be applied to high-temperature and high-pressure media, so the flange gasket can be greatly stamped, if cracks are generated on the surface of the metal gasket due to poor operation in the conventional production process, overlarge closing force can be borne in the later period, the cracks exist, the stress is uneven, the gasket can be easily broken, the sealing performance is poor, and the condition of medium leakage is generated.
Conventional seal face crack identification may use edge identification, but one type of seal wrap gasket exhibits a condition of a middle black, with the outer and inner rings both being metallic, the black area being a non-metallic filled ring, the outer metal being referred to as the outer ring and the inner metal being referred to as the inner ring. It is difficult to obtain a defect region using either edge recognition or threshold segmentation when cracks occur mainly in the filled ring region.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for identifying the defects of the sealing surface of the valve, which adopts the following technical scheme:
identifying and acquiring a wound gasket image, and segmenting the image by utilizing a gray level histogram to obtain an inner ring area and an outer ring area; respectively calculating the gray level uniformity degree in the gray level interval corresponding to the two areas, and acquiring an image with the gray level uniformity degree larger than a threshold value;
setting a window with a fixed size to perform sliding window processing on the gasket winding image, and calculating gray value difference values between a central pixel point and other pixel points in the window to obtain a central deviation value; acquiring pixel points with the central deviation value larger than a threshold value, calculating the central deviation value of the pixel points vertical to the gradient direction of the pixel points until the central deviation value is smaller than the threshold value, and acquiring all traversed pixel points to form a crack area for winding the gasket;
judging whether the crack region belongs to an inner ring region or an outer ring region according to the distance from the pixel points in the crack region to the original point of the ring of the gasket, and selecting the pixel points at the set positions in the crack region to form a possible defect region; calculating the cracking possibility according to the distance of the pixel points in the possible defect area;
when the cracking possibility is smaller than a threshold value, calculating the possibility of cracks in the crack area according to the gradient of the pixel points in the crack area; and judging the defects of the valve sealing gasket according to the possibility of cracks existing in the crack area and the possibility threshold.
Preferably, the method for acquiring the gray level uniformity degree in the gray level interval corresponding to the region specifically includes:
wherein the content of the first and second substances,is a regionThe degree of uniformity of the gray scale of the corresponding gray scale interval,is a sectionThe highest frequency value of the inner-band,are adjacent gray scale interval values.
Preferably, the method for acquiring the central deviation value specifically includes:
wherein the content of the first and second substances,the value of the center deviation is represented,is the gray value of each point in the neighborhood of the central point, H is the gray value of the central pixel point, i represents the ith pixel in the neighborhoodAnd (4) point.
Preferably, the step of judging whether the crack region belongs to the inner ring region or the outer ring region according to the distance from the pixel point in the crack region to the origin of the gasket ring is specifically as follows:
establishing a rectangular coordinate system by taking the center of the gasket ring as an origin to obtain coordinates of pixel points in a crack region, and calculating distance values between the inner edge of the inner ring and the outer edge of the outer ring and the origin due to the fact that the widths of the middle filling ring on the gasket of the inner ring and the gasket of the outer ring are approximately the same as the widths of the inner ring and the gasket of the outer ring;
Distance between pixel point in crack region and originWhen the crack region belongs to the outer ring region;
distance between pixel point in crack region and originThe crack region then belongs to the inner ring region.
Preferably, the step of selecting the pixel points at the set positions in the crack region to form the possible defect region specifically includes:
respectively obtaining the coordinates of the pixel points farthest away from the center of the circular ring on the inner ring crack and the coordinates of the pixel points nearest to the center of the circular ring on the outer ring crack, and recording the coordinates asAndobtaining pixel pointsAndthe connection line with the center of the circular ring is extended to the inner edge of the outer ring, and the two connection lines and the filling are replaced to form the possibilityA defective area.
Preferably, the calculating the cracking possibility according to the distance between the pixel points in the possible defect area specifically includes:
in the formulaThe coordinates of the pixel points on the inner ring cracks farthest from the center of the ring,the coordinates of the pixel points on the outer ring cracks closest to the center of the circular ring.
Preferably, the determining the defect of the valve sealing gasket according to the possibility of the crack existing in the crack region and the threshold of the possibility is specifically:
when the possibility of the cracks is smaller than or equal to the possibility threshold value, the corresponding sealing winding gasket has defects and is an unqualified product; when the possibility of crack existence is larger than the possibility threshold value, the inner ring and the outer ring need to be produced again, and the filling ring has no defects.
The embodiment of the invention at least has the following beneficial effects:
according to the method, the area with possible defects of the filling ring is positioned according to the cracks of the inner ring area and the outer ring area, the defect of redundant calculated amount when pixel-by-pixel point identification is carried out on the filling layer is avoided, and the calculated amount is greatly reduced. Meanwhile, the possibility that the defect exists in the possible defect area of the filling layer is extracted by analyzing the directions and the distances of the cracks of the inner ring and the outer ring, the problem that the defects of the filling layer cannot be identified accurately or even cannot be identified conventionally is solved, and the accuracy of the identification efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for identifying defects on a valve sealing surface according to the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description is provided for a method for identifying defects of a valve sealing surface according to the present invention, and its specific implementation, structure, features and effects thereof, with reference to the accompanying drawings and preferred embodiments. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the valve sealing surface defect identification method provided by the invention in detail with reference to the accompanying drawings.
The embodiment is as follows:
the main purposes of the invention are: the method comprises the steps of positioning a region where a filling ring possibly has defects by identifying the defects of an inner ring region and an outer ring region of a wound gasket, and identifying and extracting crack defects.
The specific scenes aimed by the invention are as follows: the winding gasket in the valve sealing part has crack defects caused by poor operation in various operation processes such as surfacing and the like.
Referring to fig. 1, a flowchart of a method for identifying a defect on a sealing surface of a valve according to an embodiment of the present invention is shown, where the method includes the following steps:
identifying and acquiring a wound gasket image, and segmenting the image by utilizing a gray level histogram to obtain an inner ring area and an outer ring area; and respectively calculating the gray level uniformity degree in the gray level interval corresponding to the two areas, and acquiring the image with the gray level uniformity degree larger than a threshold value.
Firstly, a camera is placed above a production line, when a wound gasket is transported to the position right below the camera, image acquisition is carried out, because the acquired image comprises a background area, semantic segmentation is carried out on the acquired image, the background area is set to be black, and the gasket area is kept with primary colors. And performing graying processing on the image of the winding gasket after the semantic segmentation processing to obtain an image of the winding gasket.
It should be noted that before defect identification of the sealing gasket, it is required to briefly analyze whether a defect may exist, if a defect may exist, the defect of the inner and outer ring regions is identified to locate the region where the defect may exist in the filling layer, and the possibility of the defect existing in the current region is analyzed, so as to provide data support for subsequent crack identification.
The winding gasket needs to be subjected to subarea analysis when the gasket is analyzed to determine whether possible defects exist, because the possibility of the defects existing in a conventional analysis image is analyzed through the gray level uniformity degree of the image, and the colors of the inner ring and the outer ring of the winding gasket are different from the colors of the filling rings, the overall gray level uniformity analysis cannot be performed on the whole area, and the subarea analysis is needed. Therefore, the image needs to be divided into regions first.
And then, constructing a gray histogram of the image according to gray values of pixel points in the wound gasket image, and dividing the image into two parts according to gray values according to the gray difference between the metal colors of the inner ring and the outer ring and the black of the filling ring, wherein one part is a gray interval in which the pixel points of the metal colors are located, and the other part is a gray interval in which the black pixel points are located.
Selecting the gray value corresponding to the lowest wave trough on the gray histogram as the gray segmentation threshold of metal color and black, dividing the gray on the gray histogram into two intervals, wherein the two gray intervals respectively correspond to one region and respectively correspond to an inner ring region and an outer ring region, namelyIs a black area and is a black area,is a metallic color region.
And finally, calculating the gray level uniformity degree of each gray level interval corresponding to each region, and expressing the gray level uniformity degree as follows by using a formula:
wherein the content of the first and second substances,is a regionThe degree of uniformity of the gray scale of the corresponding gray scale interval,is a section ofThe highest frequency value of the inner-band,are adjacent gray scale interval values.
The gray scale is distributed in order to obtain the range occupied by each gray scale interval, if the occupied range is large, the gray scale is discrete, otherwise, the gray scale is concentrated when the occupied range is small.In order to calculate the concentration of the frequencies in a gray scale interval. If the interval range is small and the internal maximum frequency value is larger, the pixels in the gray scale interval are more concentrated, and if the interval range is large and the internal maximum frequency value is small, the gray scale interval is more dispersed.
The more concentrated the gray scale intervals, the less likely the defect is present, whereas the more dispersed the gray scale intervals, the more likely the defect is present. SelectingFor subsequent defect identification.
The concentration degree of the pixel frequency of the gray level interval in each area is analyzed to obtain the possibility of defects in the area, the areas with high possibility are subjected to subsequent analysis, and the areas without possibility are not subjected to subsequent analysis, so that the calculation amount is greatly reduced, and the efficiency is improved.
Setting a window with a fixed size to perform sliding window processing on the wound gasket image, and calculating gray value difference values between a central pixel point and other pixel points in the window to obtain a central deviation value; and acquiring pixel points with the central deviation value larger than the threshold, calculating the central deviation value of the pixel points vertical to the gradient direction of the pixel points until the central deviation value is smaller than the threshold, and acquiring all traversed pixel points to form a crack area for winding the gasket.
The crack defect of the filling ring region is difficult to directly identify, but generally, the serious crack can pass through the three rings, the cracks on the inner ring and the outer ring are easy to identify, the crack defect of the inner ring and the crack defect of the outer ring are used for firstly positioning which regions of the filling ring are likely to have cracks, and the possibility of the crack existence of the filling ring is analyzed according to the specific degree of the defect of the inner ring and the defect of the outer ring.
The inner ring metal and the outer ring metal are made of steel plates, the gray of the steel plates is not absolutely uniform, the conditions of zero scattered and irregular pixel points with gray jump exist, but the gray value change of the pixel points in a crack area can also form a curve or a straight line, the gradient of the steel plates is scattered and has no seal, but the gradient of the cracks is similar, and a uniform gradient direction exists.
Setting a window with a fixed size to perform sliding window processing on the wound gasket image, setting the size of the window to be 3 × 3 in this embodiment, starting to slide from the outer ring by using a sliding window with the size of 3 × 3, judging the gray variance between each central point and each point in the eight neighborhoods during each sliding, and obtaining a central offset value corresponding to the central pixel point, which is expressed by a formula:
wherein the content of the first and second substances,the value of the center deviation is represented,the gray value of each point in the neighborhood of the central point is H, the gray value of the central pixel point is H, and i represents the ith pixel point in the neighborhood.And calculating the deviation between the gray value of the neighborhood pixel and the gray value of the central pixel by taking the gray value of the central pixel as a reference.
The central deviation value calculates the mean value of the deviation square sum of the gray value of each neighborhood pixel point and the gray value of the central point thereof, and reflects the total deviation degree of the gray value of the central pixel point and the gray value of the neighborhood pixel points.
Setting a deviation threshold, when the deviation degree is larger, calculating the gradient direction of the central pixel point, and selecting the central pixel point with the gradient direction of the central pixel pointThe adjacent pixel points in the direction of the direction,the direction is the direction perpendicular to the gradient direction of the central pixel point, and is equivalent to the direction of the crack.
And calculating the central deviation value of the pixel point vertical to the gradient direction of the central pixel point, if the central deviation value of the pixel point is still larger than the deviation threshold value, continuing to calculate the gradient direction of the pixel point, selecting the pixel point adjacent to the pixel point in the direction vertical to the gradient direction, and calculating the central deviation value again. And acquiring all traversed pixels with the center deviation values larger than the deviation threshold value to form a crack area in the wound gasket image until the center deviation value of a certain pixel is smaller than the deviation threshold value. And returning to the position of the pixel point with the larger central deviation value again, and continuously sliding along the outer ring, so as to extract the crack, and processing the inner ring by using the same method.
Judging whether the crack region belongs to an inner ring region or an outer ring region according to the distance from the pixel points in the crack region to the original point of the circular ring of the gasket, and selecting the pixel points at the set positions in the crack region to form a possible defect region; and calculating the cracking possibility according to the distance of the pixel points in the possible defect area.
First, it should be noted that if there is a crack in the inner and outer rings, there is a high probability that there is a crack in the filled ring region between the inner and outer ring defects, because the crack tends to cause less crack damage to the adjacent regions of the inner and outer rings due to the larger crack generated by the filled ring. Therefore, the region which is possibly provided with defects on the filling ring is firstly positioned according to the crack regions of the inner ring and the outer ring, pixel-by-pixel analysis is avoided, and the calculation amount is reduced.
Then, a rectangular coordinate system is established by taking the center of the gasket ring as an origin to obtain the coordinates of the pixel points in the crack region, and the distance values between the inner edge of the inner ring and the outer edge of the outer ring and the origin are calculated because the widths of the middle filling ring on the gasket of the inner ring and the gasket of the outer ring are approximately the same as the widths of the inner ring and the outer ring。
For the distance from all pixel points in the crack area to the original pointThe crack belongs to the crack on the outer ring, so that the coordinate of the pixel point closest to the origin on the crack is selected。
Otherwise, when all pixel points in the crack area are away from the original pointIs a distance ofThe crack belongs to the crack on the inner ring, so that the coordinate of the pixel point on the crack which is farthest from the origin is selected。
Pixel pointAndand respectively making a connecting line of the original points, and extending the connecting line to the inner edge of the outer ring, so that an arc-shaped area formed by the two connecting lines and the filling ring is a possible defect area. The possible defect area is an area where a defect may exist on the filled ring.
Finally, the cracks of the filling ring area are difficult to identify, so that the possibility that the defects exist in the current positioning area is calculated through the directions of the cracks of the inner and outer ring areas on the two sides of the filling ring area and the distance between the cracks and the filling ring area is more reasonable. It is necessary to consider whether the two cracks begin to crack immediately adjacent the edge of the filler ring, if the two cracks can form a straight line, but the distance is much greater than the width of the filler layer, indicating that the same crack is not due to cracking of the filler layer, but two cracks are irrelevant.
Therefore, the distance between the crack on the inner ring and the crack on the outer ring and the filling layer is firstly calculated, and the cracking possibility that the crack of the inner ring and the outer ring is close to the filling ring is judged:
in the formulaThe coordinates of the pixel points on the inner ring cracks which are farthest away from the original point,and the coordinates of the pixel points on the outer ring crack closest to the origin are the endpoints on the crack closest to the filling layer.、Respectively, the minimum distance from the outer ring crack to the origin and the farthest distance from the inner ring crack to the origin.
When the cracking possibility is smaller than a threshold value, calculating the possibility of cracks in the crack area according to the gradient of the pixel points in the crack area; and judging the defects of the valve sealing gasket according to the possibility of the cracks in the crack area and the possibility threshold.
In particular whenThe distance between the two points is larger than the width of the filling layer, the two cracks are not the same, namely the filling layer has no cracks, otherwise, the distance between the two points is larger than the width of the filling layerThe distance between the two points is smaller than or equal to the width of the filling layer, and the inner and outer ring cracks are close to the filling layer, so that the possibility of belonging to one crack is high.
When the crack is in close proximity to the filling layer, i.e.Then, the possibility that two cracks form a straight line is judged. Extracting coordinate values of each pixel point on two cracks forming a possible defect area of the filling ring, and calculating the gradient direction of each pointCalculating the probability of the two cracks forming a straight line according to the gradient of each point on the two cracks:
wherein n is the total number of pixel points on the two cracks, i represents the ith pixel point,the gradient direction of each point is indicated.The mean value of the gradient directions is calculated for the subsequent calculation of the variance of the gradient directions.
And calculating the deviation between the gradient direction of each pixel point on the crack and the mean value, calculating the square sum of the deviations to obtain the overall variance, and expressing the overall deviation degree between all the pixel points and the mean value.
If the gradient directions of all pixel points on the two cracks are approximately consistent, namelyThe smaller the size, the more likely the two cracks are in the same direction, and the possibility that a straight line can be formed is very high. At the same time, the possibility of cracks in the possible defect region of the positioning of the filling layer is high when the possibility of two cracks forming a straight line is high, so that the possibility is highWhile the possibility of cracks exists as possible defect regions.
It should be noted that the cracks of the filling layer are identified by identifying the cracks in the obvious areas of the inner and outer rings to assist in identifying the cracks of the filling layer, so that the problem of difficulty in identifying the cracks of the filling layer is solved, the calculated amount is reduced, and the redundant calculation for identifying the filling layer pixel by pixel is avoided.
Meanwhile, the cracks of the filling layer are not obvious, and the texture of the cracks in the image acquired by the graphite material of the filling layer is not obvious, so that the cracks of the filling layer can be identified more effectively indirectly through the cracks in the inner and outer ring copper plate areas.
Setting a possibility threshold, wherein when the possibility of cracks is less than or equal to the possibility threshold, the corresponding sealing winding gasket has defects and is an unqualified product; when the possibility of the existence of the crack is greater than the possibility threshold value, the inner ring and the outer ring need to be produced again, and the filling ring has no defects.
In particular whenThe possibility that the possible defect positioned at present has a crack is considered to be very high, and the possible defect can be extracted to be used as an unqualified product; the extracted regions include crack regions of the inner and outer rings and possible defect regions of the filler layer. In addition to the need to produce the inner and outer rings again, the filler rings also need to be produced again.
Otherwise ifThe cracks of the inner ring and the outer ring are not the same, namely the filling layer has no cracks, only the inner ring and the outer ring need to be produced again at the moment, and the filling ring can be used for assembling a new winding gasket again.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not cause the essential features of the corresponding technical solutions to depart from the scope of the technical solutions of the embodiments of the present application, and are intended to be included within the scope of the present application.
Claims (7)
1. A method for identifying defects of a valve sealing surface is characterized by comprising the following steps:
identifying and acquiring a wound gasket image, and segmenting the image by utilizing a gray level histogram to obtain an inner ring area and an outer ring area; respectively calculating the gray level uniformity degree in the gray level interval corresponding to the two areas, and acquiring an image with the gray level uniformity degree larger than a threshold value;
setting a window with a fixed size to perform sliding window processing on the wound gasket image, and calculating gray value difference values between a central pixel point and other pixel points in the window to obtain a central deviation value; acquiring pixel points of which the central deviation values are larger than a threshold value, calculating the central deviation values of the pixel points vertical to the gradient direction of the pixel points until the central deviation values are smaller than the threshold value, and acquiring all traversed pixel points to form crack regions for winding the gaskets;
judging whether the crack region belongs to an inner ring region or an outer ring region according to the distance from the pixel points in the crack region to the original point of the gasket ring, and selecting the pixel points at the set positions in the crack region to form a possible defect region; calculating the cracking possibility according to the distance between the pixel points in the possible defect area;
when the cracking possibility is smaller than a threshold value, calculating the possibility of cracks in the crack area according to the gradient of the pixel points in the crack area; and judging the defects of the valve sealing gasket according to the possibility of cracks existing in the crack area and the possibility threshold.
2. The method for identifying the defects of the valve sealing surface according to claim 1, wherein the method for acquiring the gray scale uniformity degree in the gray scale interval corresponding to the region specifically comprises the following steps:
3. The method for identifying the defect of the valve sealing surface according to claim 1, wherein the method for acquiring the central deviation value specifically comprises the following steps:
4. The method for identifying the defect of the valve sealing surface according to claim 1, wherein the step of judging whether the crack region belongs to the inner ring region or the outer ring region according to the distance from the pixel point in the crack region to the origin of the circular ring of the gasket is specifically as follows:
establishing a rectangular coordinate system by taking the center of the gasket ring as an origin to obtain coordinates of pixel points in a crack region, and calculating distance values between the inner edge of the inner ring and the outer edge of the outer ring and the origin due to the fact that the widths of the middle filling ring on the gasket of the inner ring and the gasket of the outer ring are approximately the same as the widths of the inner ring and the gasket of the outer ring;
Distance between pixel point in crack region and originWhen the crack region belongs to the outer ring region;
5. The method for identifying the defects of the valve sealing surface according to claim 1, wherein the step of selecting the pixel points at the set positions in the crack region to form the possible defect region specifically comprises the following steps:
respectively obtaining the coordinates of the pixel point farthest from the center of the circular ring on the crack of the inner ring and the coordinates of the pixel point nearest to the center of the circular ring on the crack of the outer ring, and recording the coordinates asAndobtaining pixel pointsAndand a connecting line with the center of the circular ring is extended to the inner edge of the outer ring, and the two connecting lines and the filling are replaced to form a possible defect area.
6. The method for identifying the defects of the valve sealing surface according to claim 5, wherein the calculation of the cracking possibility according to the distance between the pixel points of the possible defect area specifically comprises the following steps:
7. The method for identifying the defect of the valve sealing surface according to claim 1, wherein the step of judging the defect of the valve sealing gasket according to the possibility of the crack existing in the crack area and the possibility threshold is specifically as follows:
when the possibility of the cracks is smaller than or equal to the possibility threshold value, the corresponding sealing winding gasket has defects and is an unqualified product; when the possibility of crack existence is larger than the possibility threshold value, the inner ring and the outer ring need to be produced again, and the filling ring has no defects.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211225419.8A CN115294134B (en) | 2022-10-09 | 2022-10-09 | Valve sealing surface defect identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211225419.8A CN115294134B (en) | 2022-10-09 | 2022-10-09 | Valve sealing surface defect identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115294134A true CN115294134A (en) | 2022-11-04 |
CN115294134B CN115294134B (en) | 2023-01-20 |
Family
ID=83833865
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211225419.8A Active CN115294134B (en) | 2022-10-09 | 2022-10-09 | Valve sealing surface defect identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115294134B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116823825A (en) * | 2023-08-29 | 2023-09-29 | 山东海德尼克液压科技有限公司 | Intelligent identification method for casting defects of valve fittings |
CN117291907A (en) * | 2023-11-22 | 2023-12-26 | 百强阀门集团有限公司 | Valve sealing surface detection method and system |
CN117764986A (en) * | 2024-02-22 | 2024-03-26 | 宝鸡世邦钛制品有限公司 | titanium plate surface defect detection method based on image processing |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111179243A (en) * | 2019-12-25 | 2020-05-19 | 武汉昕竺科技服务有限公司 | Small-size chip crack detection method and system based on computer vision |
CN114862862A (en) * | 2022-07-11 | 2022-08-05 | 江苏大田阀门制造有限公司 | Pump body cold shut defect identification method and system based on image processing |
CN114972329A (en) * | 2022-07-13 | 2022-08-30 | 江苏裕荣光电科技有限公司 | Image enhancement method and system of surface defect detector based on image processing |
CN115018853A (en) * | 2022-08-10 | 2022-09-06 | 南通市立新机械制造有限公司 | Mechanical component defect detection method based on image processing |
CN115018765A (en) * | 2022-04-24 | 2022-09-06 | 海门市博洋铸造有限公司 | Powder metallurgy part finished product detection method based on gray level gradient co-occurrence matrix |
CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
-
2022
- 2022-10-09 CN CN202211225419.8A patent/CN115294134B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111179243A (en) * | 2019-12-25 | 2020-05-19 | 武汉昕竺科技服务有限公司 | Small-size chip crack detection method and system based on computer vision |
CN115018765A (en) * | 2022-04-24 | 2022-09-06 | 海门市博洋铸造有限公司 | Powder metallurgy part finished product detection method based on gray level gradient co-occurrence matrix |
CN114862862A (en) * | 2022-07-11 | 2022-08-05 | 江苏大田阀门制造有限公司 | Pump body cold shut defect identification method and system based on image processing |
CN114972329A (en) * | 2022-07-13 | 2022-08-30 | 江苏裕荣光电科技有限公司 | Image enhancement method and system of surface defect detector based on image processing |
CN115018853A (en) * | 2022-08-10 | 2022-09-06 | 南通市立新机械制造有限公司 | Mechanical component defect detection method based on image processing |
CN115311301A (en) * | 2022-10-12 | 2022-11-08 | 江苏银生新能源科技有限公司 | PCB welding spot defect detection method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116823825A (en) * | 2023-08-29 | 2023-09-29 | 山东海德尼克液压科技有限公司 | Intelligent identification method for casting defects of valve fittings |
CN116823825B (en) * | 2023-08-29 | 2023-12-05 | 山东海德尼克液压科技有限公司 | Intelligent identification method for casting defects of valve fittings |
CN117291907A (en) * | 2023-11-22 | 2023-12-26 | 百强阀门集团有限公司 | Valve sealing surface detection method and system |
CN117291907B (en) * | 2023-11-22 | 2024-01-30 | 百强阀门集团有限公司 | Valve sealing surface detection method and system |
CN117764986A (en) * | 2024-02-22 | 2024-03-26 | 宝鸡世邦钛制品有限公司 | titanium plate surface defect detection method based on image processing |
CN117764986B (en) * | 2024-02-22 | 2024-05-07 | 宝鸡世邦钛制品有限公司 | Titanium plate surface defect detection method based on image processing |
Also Published As
Publication number | Publication date |
---|---|
CN115294134B (en) | 2023-01-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115294134B (en) | Valve sealing surface defect identification method | |
CN113989280B (en) | Steel structure welding crack defect detection method based on image processing technology | |
CN114862862B (en) | Pump body cold shut defect identification method and system based on image processing | |
CN111758024B (en) | Defect detection method and device | |
CN114937039B (en) | Intelligent detection method for steel pipe defects | |
CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
CN106404793B (en) | Bearing sealing element defect detection method based on vision | |
CN115439474B (en) | Rapid positioning method for power equipment fault | |
CN103543394A (en) | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment | |
CN116740070B (en) | Plastic pipeline appearance defect detection method based on machine vision | |
CN115115638B (en) | Oil leakage detection and judgment method for hydraulic system | |
CN115690108A (en) | Aluminum alloy rod production quality evaluation method based on image processing | |
CN110648349A (en) | Weld defect segmentation method based on background subtraction and connected region algorithm | |
CN117314912B (en) | Visual detection method and system for welding defects on surface of welded pipe | |
CN115965623B (en) | Surface flaw detection method and system in transformer production | |
CN116934740A (en) | Plastic mold surface defect analysis and detection method based on image processing | |
CN111667470A (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
CN115272336A (en) | Metal part defect accurate detection method based on gradient vector | |
CN117495852B (en) | Digital printing quality detection method based on image analysis | |
CN117315289B (en) | Aeroengine blade contour edge detection method based on image processing | |
CN113298775B (en) | Self-priming pump double-sided metal impeller appearance defect detection method, system and medium | |
CN117218124A (en) | Copper-aluminum switching surface processing quality detection method | |
CN108805843B (en) | Tunnel concrete lining seam removing method based on translation and extension of straight line segment | |
CN113361541A (en) | Feature extraction method for defects of underground drainage pipeline |
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 |