CN114782303A - Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics - Google Patents

Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics Download PDF

Info

Publication number
CN114782303A
CN114782303A CN202210101447.2A CN202210101447A CN114782303A CN 114782303 A CN114782303 A CN 114782303A CN 202210101447 A CN202210101447 A CN 202210101447A CN 114782303 A CN114782303 A CN 114782303A
Authority
CN
China
Prior art keywords
boundary
grinding
deformation
degree
boundary pixel
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
Application number
CN202210101447.2A
Other languages
Chinese (zh)
Inventor
李金艳
聂进
肖梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changan University
Huanggang Polytechnic College
Original Assignee
Changan University
Huanggang Polytechnic College
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changan University, Huanggang Polytechnic College filed Critical Changan University
Priority to CN202210101447.2A priority Critical patent/CN114782303A/en
Publication of CN114782303A publication Critical patent/CN114782303A/en
Pending legal-status Critical Current

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
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Geometry (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

The invention provides a method for detecting the abnormal deformation degree of an abrasive dust based on boundary distribution characteristics, which comprises the following steps: step 1, segmenting the obtained four-ball friction grinding spot image to obtain a grinding spot segmentation image; step 2, obtaining a boundary pixel map according to the grinding and dividing map; step 3, calculating the grinding deformation degree according to the boundary pixel image; step 4, detecting the abnormal deformation of the grinding spots according to the obtained deformation degree of the grinding spots; the method can realize the rapid comparison of the deformation degrees of a plurality of grinding spots and the detection of the abnormal deformation degree of the grinding spots, and has the advantages of simplicity, high efficiency, no need of manual assistance in the whole process and the like.

Description

Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics
Technical Field
The invention relates to the technical field of image test data analysis and processing, in particular to a method for detecting the abnormal deformation degree of grinding spots based on boundary distribution characteristics.
Background
The investigation result of the Chinese institute of engineering consulting project Friction science and engineering application status and development strategy research shows that: in 2006, the loss of China caused by friction and abrasion reaches about 9500 million yuan, which accounts for 4.5% of the total production value (GDP) in China in the current year. In addition, if wear develops, it can cause part failure and machine failure, with even catastrophic consequences. The lubricant with good performance is a lubricating medium for reducing the friction resistance of the friction pair and slowing down the abrasion of the friction pair, and can play roles in cooling, cleaning, preventing pollution and the like on the friction pair. Therefore, timely and accurate measurement of the performance of the lubricant is particularly important for protecting machinery and reducing energy consumption. The four-ball friction wear testing machine is widely applied to the lubricating oil friction coefficient measuring test due to the characteristics of convenient operation, simple structure, short testing period, small oil consumption, low cost and the like.
China petrochemical industry standards (GB-T12583-1998 and H-T0762-2005) stipulate the test process of the friction coefficient of the lubricating oil, and define the observation method of the appearance characteristics of the wear spots: the shape of the wear-resistant coating is generally circular or oval, when the wear-resistant coating is seriously deformed, the wear-resistant coating cannot be used for the test process of the friction coefficient of the lubricating oil, and a running-in test needs to be carried out again, so that the shape characteristic of the wear-resistant coating is quickly and accurately judged, and the wear-resistant coating is very important for judging the appearance of the wear-resistant coating and the effectiveness of the test. However, at present, no research on the automatic detection of the grinding spot deformation in the four-ball friction test appears, or a tester carries out qualitative judgment according to experience, so that subjective judgment errors are inevitably generated, and the method is neither scientific nor objective, and has no strong practical guiding significance.
Disclosure of Invention
The invention aims to provide a method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics, and the method overcomes the defects in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides a method for detecting the abnormal deformation degree of an abrasive spot based on boundary distribution characteristics, which comprises the following steps:
step 1, segmenting the obtained four-ball friction grinding spot image to obtain a grinding spot segmentation image;
step 2, obtaining a boundary pixel map according to the grinding and dividing map;
step 3, calculating the grinding deformation degree according to the boundary pixel image;
and 4, detecting the abnormal grinding deformation according to the obtained grinding deformation degree.
Preferably, in step 2, the boundary pixel map is obtained according to the scrub segmentation map, and the specific method is as follows:
calculating the position size of the grinding spot segmentation graph;
and (2) obtaining a boundary pixel map according to the position size obtained in the step (1) by combining the following formula:
Figure BDA0003492405940000021
wherein A is a grinding spot boundary diagram; a (x, y) ═ 1 indicates that the pixel (x, y) is a boundary pixel; a (x, y) ═ 0 indicates that the pixel (x, y) is a non-boundary pixel; k and l respectively represent index variables of rows and columns, are integers, and take values of-1, 0 and 1 respectively.
Preferably, in step 3, the scrub deformation degree is calculated according to the boundary pixel map, and the specific method is as follows:
respectively calculating the boundary smoothness of the boundary pixel map, the deviation full-range of the boundary pixel map, the deviation dispersion characteristic of the boundary pixel map and the number of boundary pixels corresponding to the preset deformation of the boundary pixel map;
and calculating to obtain the grinding deformation degree corresponding to the boundary pixel map according to the boundary smoothness of the obtained boundary pixel map, the deviation full-range of the boundary pixel map, the deviation dispersion characteristic of the boundary pixel map and the boundary pixel number corresponding to the preset deformation of the boundary pixel map.
Preferably, the boundary smoothness of the boundary pixel map is calculated according to the following formula:
Figure BDA0003492405940000022
wherein, Z1Represents the smoothness of the scrub boundary; num (a) is the number of pixels of the boundary pixel map; 2 π r is the perimeter of the plaque segmentation map.
Preferably, the full range of the deviation of the boundary pixel map is calculated by the following specific method:
calculating the center distance and the deviation degree of the boundary pixel map;
and calculating the deviation degree full distance of the boundary pixel map according to the center distance and the deviation degree of the obtained boundary pixel map.
Preferably, the dispersion characteristic of the boundary deviation degree is calculated according to the following formula:
Figure BDA0003492405940000031
Figure BDA0003492405940000032
wherein Z is3Is the average value of the boundary deviation degrees; z is a linear or branched member4Is the standard deviation of the boundary.
Preferably, the number of boundary pixels corresponding to a predetermined deformation amount of the boundary pixel map is calculated according to the following formula:
Figure BDA0003492405940000033
wherein, Z5The deformation proportion is a preset deformation quantity; pαThe number of boundary pixels when the preset deformation is alpha is set; num (a) is the total boundary pixel; alpha is a preset deformation quantity, and the value range of alpha is 0 according to the expert experience<α<1。
Preferably, the degree of deformation of the abrasive grain is calculated according to the following formula:
Figure BDA0003492405940000034
wherein H is the deformation degree of the grinding spots; gamma raykIs the weight coefficient of the kth feature.
Preferably, in step 4, the degree of abnormal deformation of the grinding spot is detected according to the following formula:
Figure BDA0003492405940000035
wherein fl is a mark of abnormal deformation, and represents that the shape of the abrasion mark is deformed and non-circular when fl is 1, and represents that the shape of the abrasion mark is not deformed and circular when fl is 0; beta is the deformation threshold.
Compared with the prior art, the invention has the beneficial effects that:
according to the method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics, the grinding spot images are collected by using image collection equipment or a scanning electron microscope (both have an amplification function), the automatic segmentation of the grinding spot areas can be realized by using an image analysis processing technology, the speed and the precision of the segmentation are improved, and meanwhile, the workload of manual segmentation is greatly reduced; starting from the boundary pixels of the grinding spots, the grinding spot boundary pixels are defined, the center distance of the boundary pixels is calculated, and a foundation is laid for the representation of the distribution characteristics of the subsequent boundary pixels; the quantity and distribution characteristics of the boundary pixels are quantitatively described by using multiple image features, and the establishment and expression of characteristic indexes such as boundary smoothness, deviation and the like are realized; the method has the advantages of simplicity, high efficiency, no need of manual assistance in the whole process and the like, and is very suitable for developing automatic analysis and processing software of four-ball friction test data.
Drawings
FIG. 1 is an image f of an abrasion mark;
FIG. 2 is a sectional view of the whetting plaque R;
FIG. 3 shows (x)O,yO) Label E of (365.2125,465.3137)O；
FIG. 4 is (x)O,yO) Label E of (465.2125,485.3137)O；
Fig. 5 is a diagram of a boundary pixel set a.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The specific implementation steps are as follows:
step S0: and (4) collecting an abrasion image. After the four-ball friction test, the surface of the steel ball can form grinding spots (less than or equal to 1mm) which are not observable by naked eyes, and a special acquisition device such as a high power microscope or a scanning electron microscope is needed to acquire a grinding spot image f, as shown in fig. 1.
Step S1: and (4) segmenting the grinding image. Segmentation of the scrub image includes manual segmentation and automatic segmentation, which aims to distinguish the scrub from the background. Compared with a manual segmentation method, the automatic segmentation method has the advantages of high segmentation precision and high segmentation speed. The automatic segmentation method specifically comprises the steps of establishing a bipolar value filtering difference measurement operator, carrying out initial segmentation on the grinding spots, and subdividing and accurately segmenting the grinding spot region boundary by adopting a gray scale and distance dual-constraint boundary, and comprises the following steps: graying, denoising, initial segmentation of a wear-scar area, fine segmentation of a double-constrained boundary and the like, and the algorithm has good segmentation effect on the boundary and high running speed.
In this example, an automatic segmentation method was used to obtain a scrub spot segmentation map R as shown in fig. 2, in which white and black areas are a scrub spot and a background, respectively.
Step S2: and extracting size parameters of the speckle segmentation chart. And (3) the divided grinding spots are equivalent to a standard circle, and the size parameters of the grinding spot division graph can be described by the size parameters of the circle: the position of the center C of the speckle pattern, the area S and the radius r. The position of the center C of the grinding spot segmentation chart is expressed by two-dimensional row and column coordinates of a pixel coordinate system as (x)C,yC) Wherein x isCAnd yCRespectively a line number and a column number; the area refers to the number of pixels of the grinding spot area and is represented by S; the radius refers to the radius value of the grinding spot segmentation chart and is expressed by r, and the expression is shown as (1-4):
Figure BDA0003492405940000051
Figure BDA0003492405940000052
S＝num(R) (3)
Figure BDA0003492405940000053
wherein, (x, y) is the coordinate of any pixel in the speckle segmentation map; m and N are respectively the maximum row number and the maximum column number of the grinding spot segmentation graph R; r (x, y) represents a value of a pixel (x, y) of the speckle division map R, and R is a binary image; num () is a statistical operator; num (R) is the total number of pixels of the lesion area in the lesion segmentation map R.
In this embodiment, the size parameters of the scrub splitting pattern are:
xC＝365.2125，yC465.3137, S396979 and r 355.48.
Step S3: and extracting the boundary pixels of the grinding spots. The invention starts from the boundary pixels of the grinding spots, considers the quantity, the distribution characteristics and the like, and judges the deformation degree of the grinding spots, so that the extraction of the boundary pixels of the grinding spots is the basis. The grinding spot boundary pixel is defined as that at least one pixel in eight neighborhoods of the pixel in the grinding spot segmentation graph R is non-grinding spot, and the expression is as follows:
Figure BDA0003492405940000061
wherein A is a grinding spot boundary diagram and is a binary diagram; a (x, y) ═ 1 denotes that the pixel (x, y) is a boundary pixel; a (x, y) ═ 0 indicates that the pixel (x, y) is a non-boundary pixel; k and l respectively represent index variables of rows and columns, are integers, and take values of-1, 0 and 1 respectively.
In this embodiment, the scrub boundary diagram a is shown in fig. 3.
Step S4: smoothness of the scrub boundary.
On the basis of the extraction of the grinding spot boundary pixels, indexes and characteristics thereof related to the grinding spot deformation degree are established. The smoothness of the grinding spot boundary refers to the ratio of the perimeter of the grinding spot boundary to the perimeter of the standard circle boundary, and is a measurement index parameter of the grinding spot shape deformation, and the larger the value is, the smoother the grinding spot shape is, namely, the higher the deformation degree of the grinding spot is:
Figure BDA0003492405940000062
wherein Z is1Represents the smoothness of the scrub boundary; num (A) is the number of pixels of the scrub boundary; 2 π r is the perimeter of the standard circle boundary.
In the present embodiment, the first and second electrodes are,
Figure BDA0003492405940000063
step S5: the center distance and the degree of deviation of the spot boundary pixels are lapped.
The distance between the centers of the boundary pixels is defined as the distance between the boundary pixels and the center C. When the distance between the centers of the boundary pixels is too large or too small, the boundary pixels are deviated from the positions where the boundary pixels should be, and the deviation degree of the boundary pixels can be quantitatively measured. The expression of the center distance and the deviation is shown as (7-8):
Figure BDA0003492405940000064
Figure BDA0003492405940000065
wherein d (x, y) is any boundary pixel (a), (b)
Figure BDA0003492405940000074
Satisfies A (x, y) 1 and the center C (x)C,yC) The distance between them; b (x, y) is the degree of deviation of any boundary pixel, the larger the value thereof, the farther the pixel is from the boundary, and when the value thereof is 0, the pixel is just on the boundary of the scrub dividing map.
In this embodiment, d (6,550) of any boundary pixel (6,550) is 369.06, and corresponding b (6,550) is 3.82%.
Step S6: the full distance of the boundary pixel deviation.
The total distance is the difference between the maximum value and the minimum value in the data set and is a measurement data setA general indicator of the degree of dispersion. Similarly, the total distance of the deviation degree of the boundary pixels can also be used for describing the width of the deviation degree of the outer boundary of the grinding spot, and the smaller the value of the total distance is, the smaller the deviation degree of the outer boundary of the grinding spot is, and vice versa. In general, the minimum value of the degree of deviation of the scrub boundary pixel is often 0, so it is more reasonable to express the full range by the maximum value of the degree of deviation directly, and the sign Z2Represents:
Figure BDA0003492405940000071
wherein Z is2Representing the full range of boundary pixel deviations.
In this embodiment, full pitch: z is a linear or branched member2＝0.151554321226492。
Step S7: dispersion characteristics of the degree of boundary deviation.
The overall distance (step S6) may reflect the degree of dispersion of the data from the whole, but it is difficult to describe the distribution form of the data, especially when noise such as friction debris is erroneously detected as wear marks, which may cause a large dispersion error of the outer contour described by the overall distance, so that a mean value and a standard deviation are further established for describing the dispersion (distribution) of the outer contour. The mean and standard deviation can reflect the dispersion degree of the data from the overall perspective, so the dispersion characteristic of the boundary deviation is also measured by two indexes of the mean and the standard deviation. A smaller average value indicates a smaller average deviation from the outer boundary of the lesion, and vice versa. Smaller standard deviations indicate more concentrated deviations from the outer boundary of the plaque near the mean, and larger standard deviations indicate more distant deviations from the mean:
Figure BDA0003492405940000072
Figure BDA0003492405940000073
wherein Z is3Is the average value of the deviation degree of the boundary; z4As a mark of degree of deviation of boundaryAnd (4) tolerance.
In the present embodiment, the average value Z of the boundary deviation degrees30.02073; standard deviation Z of boundary deviation4＝0.02188。
Step S8: and calculating the number of boundary pixels of the preset deformation.
Although the overall distance (step S6), the mean value, and the standard deviation (step S7) reflect the distribution characteristics of the data as a whole, when abnormal mutation data exists, the distribution characteristic error reflected by these three index parameters becomes large. In order to reduce the influence of abnormal mutation data, the discreteness (distribution) of the outer contour is further described by using a preset deformation quantity. The specific process is as follows:
firstly, forming a one-dimensional data set by the deviation data of the boundary, and sequencing the data according to an ascending order to obtain a sequenced deviation data set.
Next, the number of boundary pixels when the preset deformation amount is alpha is calculated, and the symbol P is usedαAnd (4) showing. On one hand, for the same grinding spot, the larger the value of alpha is, the number of boundary pixels P includedαThe more and vice versa. On the other hand, when the values of α are the same, P of the whetting spotαThe larger the size, the smaller the deformation of the grinding spot, and can be used for quantitatively describing the deformation degree of different grinding spots.
And finally, calculating the deformation proportion of the preset deformation quantity:
Figure BDA0003492405940000081
wherein Z is5The deformation proportion is a preset deformation quantity; pαThe boundary pixel number when the preset deformation is alpha is used as the boundary pixel number; num (a) is the total border pixel; alpha is a preset deformation quantity, and the value range of alpha is 0 according to expert experience<α<1。
In this embodiment, when α is 0.9, the compound is obtained
Figure BDA0003492405940000082
Step S9: the degree of lesion deformation is determined by the shape characteristics of the lesion boundary.
According to the H value of the grinding spots, the deformation degrees of different grinding spots can be quantitatively compared, and the larger the H value is, the larger the deformation degree of the grinding spot is:
Figure BDA0003492405940000083
wherein H is the deformation degree of the grinding spots; gamma raykFor the weight coefficient of the kth feature, the invention establishes 5 feature indexes, so k is 1,2,3,4 and 5, and satisfies the following conditions:
Figure BDA0003492405940000091
Zkthe value of the kth characteristic parameter is taken.
In this example, γkThe values of (k ═ 1,2,3,4,5) are:
Figure BDA0003492405940000092
and
Figure BDA0003492405940000093
obtaining:
Figure BDA0003492405940000094
step S10: and (4) detecting the abnormal deformation degree of the grinding spots.
By the uniform characteristic, the grinding spots with abnormal deformation can be judged to be used as a basis for carrying out the running-in test again, namely when the deformation degree is not less than the deformation threshold value beta, the grinding spots formed in the test deform, and the test needs to be carried out in the test process.
Figure BDA0003492405940000095
Where fl is a sign of abnormal deformation, and if fl is 1, it indicates that the shape of the wear spot is deformed and it is non-circular, and if fl is 0, it indicates that the shape of the wear spot is not deformed and it is circular.
In this embodiment, the value of the deformation threshold β is 0.2, and fl is 0, which indicates that the shape of the wear scar is not deformed and is circular.

Claims (9)

1. The method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics is characterized by comprising the following steps of:
step 1, segmenting an obtained four-ball friction wear scar image to obtain a wear scar segmentation graph;
step 2, obtaining a boundary pixel map according to the grinding segmentation map;
step 3, calculating the grinding deformation degree according to the boundary pixel image;
and 4, detecting the abnormal deformation of the grinding spots according to the obtained deformation degree of the grinding spots.
2. The method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics as claimed in claim 1, wherein in the step 2, a boundary pixel map is obtained according to the grinding spot segmentation map, and the specific method is as follows:
calculating the position size of the grinding spot segmentation chart;
and (2) obtaining a boundary pixel map according to the position size obtained in the step (1) by combining the following formula:
Figure FDA0003492405930000011
wherein A is a grinding spot boundary diagram; a (x, y) ═ 1 indicates that the pixel (x, y) is a boundary pixel; a (x, y) ═ 0 indicates that the pixel (x, y) is a non-boundary pixel; k and l respectively represent index variables of rows and columns, are integers, and take values of-1, 0 and 1 respectively.
3. The method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics as claimed in claim 1, wherein in the step 3, the deformation degree of the grinding spots is calculated according to the boundary pixel map, and the specific method is as follows:
respectively calculating the boundary smoothness of the boundary pixel map, the deviation full-range of the boundary pixel map, the deviation dispersion characteristic of the boundary pixel map and the number of boundary pixels corresponding to the preset deformation of the boundary pixel map;
and calculating to obtain the grinding deformation degree corresponding to the boundary pixel map according to the boundary smoothness of the obtained boundary pixel map, the deviation full-range of the boundary pixel map, the deviation dispersion characteristic of the boundary pixel map and the boundary pixel number corresponding to the preset deformation of the boundary pixel map.
4. The method of claim 3, wherein the boundary smoothness of the boundary pixel map is calculated according to the following formula:
Figure FDA0003492405930000021
wherein Z is1Represents the smoothness of the scrub boundary; num (a) is the number of pixels of the boundary pixel map; 2 π r is the perimeter of the plaque segmentation map.
5. The method for detecting the abnormal deformation degree of the grinding spots based on the boundary distribution characteristics as claimed in claim 3, wherein the total distance of the deviation degrees of the boundary pixel map is calculated by the following specific method:
calculating the center distance and the deviation degree of the boundary pixel map;
and calculating the deviation degree full distance of the boundary pixel map according to the center distance and the deviation degree of the obtained boundary pixel map.
6. The method of detecting the degree of abnormal deformation of a whetstone based on the boundary distribution characteristics of claim 5, wherein the dispersion characteristics of the degree of boundary deviation are calculated according to the following formula:
Figure FDA0003492405930000022
Figure FDA0003492405930000023
wherein, Z3Is the average value of the deviation degree of the boundary; z4Is the standard deviation of the boundary.
7. The method for detecting abnormal deformation degree of grinding spot based on the boundary distribution characteristics as claimed in claim 3, wherein the number of boundary pixels corresponding to the preset deformation amount of the boundary pixel map is calculated according to the following formula:
Figure FDA0003492405930000024
wherein, Z5The deformation proportion of the deformation quantity is preset; pαThe number of boundary pixels when the preset deformation is alpha is set; num (a) is the total boundary pixel; alpha is a preset deformation quantity, and the value range of alpha is 0 according to expert experience<α<1。
8. The method for detecting abnormal degree of grinding spot deformation based on boundary distribution characteristics as claimed in claim 3, wherein the degree of grinding spot deformation is calculated according to the following formula:
Figure FDA0003492405930000031
wherein H is the deformation degree of the grinding spots; gamma raykIs the weight coefficient of the kth feature.
9. The method for detecting the abnormal deformation degree of the grinding stone based on the boundary distribution characteristics as claimed in claim 1, wherein in the step 4, the abnormal deformation degree of the grinding stone is detected according to the following formula:
Figure FDA0003492405930000032
wherein fl is a mark of abnormal deformation, and represents that the shape of the abrasion mark is deformed and non-circular when fl is 1, and represents that the shape of the abrasion mark is not deformed and circular when fl is 0; beta is the deformation threshold.
CN202210101447.2A 2022-01-27 2022-01-27 Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics Pending CN114782303A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210101447.2A CN114782303A (en) 2022-01-27 2022-01-27 Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210101447.2A CN114782303A (en) 2022-01-27 2022-01-27 Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics

Publications (1)

Publication Number Publication Date
CN114782303A true CN114782303A (en) 2022-07-22

Family

ID=82423456

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210101447.2A Pending CN114782303A (en) 2022-01-27 2022-01-27 Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics

Country Status (1)

Country Link
CN (1) CN114782303A (en)

Similar Documents

Publication Publication Date Title
CN115100203B (en) Method for detecting quality of steel bar polishing and rust removal
CN110286124B (en) Machine vision-based refractory brick measuring system
CN115861291B (en) Chip circuit board production defect detection method based on machine vision
CN107341802A (en) It is a kind of based on curvature and the compound angular-point sub-pixel localization method of gray scale
CN108662983B (en) Method for detecting and calculating correlation coefficient of steel rail abrasion
CN108596872B (en) Steel rail disease detection method based on Gabor wavelet and SVM
CN102441581A (en) Machine vision-based device and method for online detection of structural steel section size
CN108177660B (en) Steel rail abrasion detection method with laser image processing step
CN110530278B (en) Method for measuring clearance surface difference by utilizing multi-line structured light
CN113838054A (en) Mechanical part surface damage detection method based on artificial intelligence
CN116152749B (en) Intelligent gear wear monitoring method based on digital twin
CN116703898A (en) Quality detection method for end face of precision mechanical bearing
CN111412864B (en) Automatic grinding crack angle detection method based on grinding crack gray scale similarity
CN115063620B (en) Bit layering based Roots blower bearing wear detection method
CN114881960A (en) Feature enhancement-based cloth linear defect detection method and system
CN111429428B (en) Method for detecting abnormal grinding image based on appearance characteristics
CN114693659A (en) Copper pipe surface cleaning effect evaluation method and system based on image processing
CN107392899B (en) Automatic detection method for horizontal angle of grinding mark of steel ball grinding spot image
CN116883402B (en) Corrugated paper production quality real-time detection method based on computer vision
CN106989672A (en) A kind of workpiece measuring based on machine vision
CN114155226A (en) Micro defect edge calculation method
CN114782303A (en) Method for detecting abnormal grinding deformation degree based on boundary distribution characteristics
CN115464745B (en) Concrete 3D printing path optimization method with variable path width
CN107358604B (en) Four-ball friction test speckle image anomaly detection method
CN106841575A (en) A kind of four ball friction tests mill spot image polishing scratch direction automatic positioning method

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