CN115308121A - Method for measuring metal plastic forming friction coefficient by adopting image recognition technology - Google Patents
Method for measuring metal plastic forming friction coefficient by adopting image recognition technology Download PDFInfo
- Publication number
- CN115308121A CN115308121A CN202210897960.7A CN202210897960A CN115308121A CN 115308121 A CN115308121 A CN 115308121A CN 202210897960 A CN202210897960 A CN 202210897960A CN 115308121 A CN115308121 A CN 115308121A
- Authority
- CN
- China
- Prior art keywords
- sample
- image
- maximum cross
- minimum end
- area
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N19/00—Investigating materials by mechanical methods
- G01N19/02—Measuring coefficient of friction between materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- 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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
A method for determining the friction coefficient of metal plastic forming by adopting an image recognition technology comprises the following steps: 1) After a metal material to be measured is manufactured into a cylindrical sample, measuring the cylindrical sample to obtain initial radius and initial height data; 2) Compressing the cylinder sample to obtain a compression sample of the cylinder, and measuring to obtain height data of the compression sample; 3) Shooting an axial view of a compressed sample, and identifying a minimum end surface area and a maximum cross section area of the compressed sample in the axial view by adopting an image identification technology; 4) Respectively extracting boundary information of the minimum end surface area and the maximum cross section area to form a boundary node matrix of the minimum end surface area and a boundary node matrix of the maximum cross section area; 5) Respectively fitting a minimum end face area circle and a maximum cross section area circle according to the boundary node matrix of the minimum end face area and the boundary node matrix of the maximum cross section area, and acquiring the radius of each circle; 6) And calculating the friction coefficient of the cylindrical sample in the compression process.
Description
Technical Field
The invention relates to the field of friction coefficient measurement, in particular to a method for measuring a metal plastic forming friction coefficient by adopting an image recognition technology.
Background
In the plastic forming process of metal, when the contact surface of the tool and the deformed metal has relative movement or has relative movement tendency, the contact surface of the tool and the deformed metal inevitably generates friction force. The friction force in plastic forming is higher in contact pressure than in mechanical transmission, a new contact surface is generated, and most of the friction force is generated at a higher temperature.
The friction force during the plastic forming of the metal plays a positive role in some situations, for example, in the processes of rolling, extruding, forging and the like, the tool is controlled to output the most appropriate load force, the flowing direction of the metal is controlled by using the friction force, a product meeting the requirements can be obtained, and the manufacturing cost of the product can be reduced to the maximum extent.
However, in most cases, this friction is very harmful, mainly in terms of modifying the stress state of the deformed metal, increasing the resistance to deformation; cause uneven deformation, resulting in additional stress and residual stress; the large friction force also causes heating, abrasion and adhesion of the mold surface, reduces the life of the mold, and the like. In order to reduce various adverse effects caused by friction, the amount of friction is often controlled by adjusting the amount of lubricant.
How to quantitatively evaluate the forming effect of metal plastic forming under different lubricating conditions is generally to determine the friction coefficient so as to deeply understand the friction force and the lubricating mechanism in the metal plastic forming process and improve the production benefit and the product quality.
At present, a ring compression method is generally adopted as a general method for measuring the friction coefficient in the metal plastic forming process, and the friction coefficient is measured by utilizing the deformation of a ring during upsetting and is used for evaluating the lubricating effect of a lubricant.
However, the use of the ring compression method for determining the friction coefficient has the following two problems:
the method has the advantages that during upsetting of the circular ring, due to uneven deformation of a blank caused by friction force, bulges appear on the cross section of the circular ring, so that the measurement error is large, and the accuracy of a measurement result is low;
and a theoretical calibration curve of the ring upsetting process needs to be established in advance, the theoretical calibration curves of different materials are different, the experimental process is complicated, and the calculation is complex.
The friction coefficient in the plastic forming process of metal can be measured by the pin-disk friction test method of ASTM G99-04, which has a high measurement accuracy, but the measurement process is extremely complicated, and a sample of a specific size is required to be prepared, which results in a high measurement cost.
In order to rapidly and accurately measure the friction coefficient in the metal plastic forming process, relevant technicians at home and abroad deeply research the friction force and the lubrication mechanism in the metal forming process and then provide various methods for calculating the friction coefficient, but various problems still exist, such as:
(1) in the technical scheme disclosed in the application No. 201410422698.6, namely the upsetting-extruding deformation testing method for the hot forging friction factor, although the die design is simple, the workpiece size measurement is simple, the condition that the workpiece shape is unstable does not exist, and the determination error is reduced, the corresponding theoretical calibration curve needs to be established in advance for different materials, and the complex data comparison work needs to be carried out repeatedly;
(2) although the device and the method for testing the single-sided friction coefficient in the hot stamping forming process, which are disclosed in application No. 201510526761.5, do not need to establish corresponding theoretical calibration curves in advance for different materials, a specially-made device for testing the single-sided friction coefficient in the hot stamping forming process is needed, the experimental process is complicated, the average value of multiple test results is needed to be taken as the friction coefficient, and the accuracy of the test results is not high;
(3) although the forward extrusion test method for the plastic forming friction coefficient and the friction factor, which is applied to the application number 201310136876.4, does not need to establish a corresponding theoretical calibration curve in advance for different materials, a conical die is also needed to be manufactured by adopting a metal material to be tested, and the friction coefficient is calculated according to parameters such as extrusion load, material yield stress, actual diameter of a sample, geometric size data of the conical die and the like, so that the calculation process is complex, and the accuracy of a test result is not guaranteed.
Disclosure of Invention
The invention aims to provide a method for measuring the friction coefficient of metal plastic forming by adopting an image recognition technology, which aims at overcoming the corresponding defects in the prior art, does not need to prepare a complicated testing device or a mold in advance, does not need to establish a corresponding theoretical calibration curve in advance aiming at different materials, does not need to acquire various parameters involved in the metal plastic forming process, only uses a camera or a camera to acquire the geometric parameters of a metal sample before and after plastic forming by adopting the image recognition technology, and can accurately measure the friction coefficient in the metal plastic forming process by using a friction coefficient calculation formula provided by the invention.
The purpose of the invention is realized by adopting the following scheme: a method for determining the friction coefficient of metal plastic forming by adopting an image recognition technology comprises the following steps:
1) After a metal material to be measured is manufactured into a cylindrical sample, measuring the cylindrical sample to obtain initial radius and initial height data;
2) Compressing the cylindrical sample to obtain a compressed sample of the cylinder, and measuring to obtain height data of the compressed sample;
3) Shooting an axial view of a compressed sample, and identifying a minimum end surface area and a maximum cross section area of the compressed sample in the axial view by adopting an image identification technology;
4) Respectively extracting boundary information of the minimum end surface area and the maximum cross section area to form a boundary node matrix of the minimum end surface area and a boundary node matrix of the maximum cross section area;
5) Respectively fitting a minimum end face area circle and a maximum cross section area circle according to the boundary node matrix of the minimum end face area and the boundary node matrix of the maximum cross section area, and acquiring the radius of each circle;
6) The coefficient of friction during compression of the cylindrical test piece was calculated according to the following formula:
where μ is the coefficient of friction during compression of the cylindrical sample, R t Radius of the circle of the smallest end surface area, R m Radius of the largest cross-sectional area circle, H is the height of the compressed sample, H 0 Is the initial height, R, of the cylindrical sample 0 Is the initial radius of the cylindrical sample.
Preferably, the cylindrical sample is made of the metal material to be tested according to the specification of metal compression test method with the standard number of GB 7314-1987.
Preferably, the compressed sample is obtained by compressing a cylindrical sample according to the specification in the metal compression test method of standard number GB 7314-1987.
Preferably, the process of identifying the axial view of the compressed sample using image recognition techniques is as follows:
3-1) converting the axial view of the shot compressed sample into a gray image, and converting the gray image into a binary image;
3-2) obtaining a maximum cross section threshold value from the binary image by adopting a maximum inter-class variance method, and obtaining a minimum end face threshold value from the binary image by adopting an iterative threshold value method;
3-3) extracting a plurality of pixel points with the gray values of 0 in the binary image according to the maximum cross section threshold value to form a maximum cross section area of the compressed sample;
and 3-4) extracting a plurality of pixel points with the gray values of 0 from the binary image according to the minimum end face threshold value to form a minimum end face area of the compressed sample.
Preferably, if the axial view of the compressed sample is a true color image, the axial view of the compressed sample is converted into a grayscale image according to the following steps:
3-1-1) calculating a weighted sum of the R, G and B components of the true color pattern, converting the RGB values to gray values according to the following formula:
I g =0.2989*R+0.5870*G+0.1140*B
in the formula I g The gray value of the gray image is obtained, R is an R channel component of the true color image, G is a G channel component of the true color image, and B is a B channel component of the true color image;
3-1-2) converting the axial view of the compressed sample into a gray image according to the gray value obtained by calculation.
Preferably, the minimum end surface area circle and the maximum cross-sectional area circle are both obtained by least square fitting.
Preferably, the boundary information is coordinates of each point on each regional boundary line.
The invention has the following beneficial effects:
(1) a complex test device or a mold does not need to be prepared in advance;
(2) corresponding theoretical calibration curves do not need to be established in advance for different materials, and tedious data comparison work does not need to be carried out repeatedly by adopting the theoretical calibration curves;
(3) the method has the advantages that the geometric parameters of the metal sample before and after plastic deformation are obtained by using a camera or a camera and adopting the existing mature image recognition technology, the friction coefficient in the metal plastic forming process can be conveniently and quickly measured by using the friction coefficient calculation formula provided by the invention, the whole testing process is simple in step, convenient and fast to use and easy to realize, and various parameters involved in the metal plastic deformation process do not need to be obtained.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of the present invention for measuring the friction coefficient of plastic forming of metal.
Detailed Description
As shown in fig. 1 to 2, a method for determining a friction coefficient of plastic forming of a metal by using an image recognition technique includes the steps of:
1) After the metal material to be measured is made into a cylindrical sample according to the standard requirements, measuring the cylindrical sample to obtain an initial radius R 0 And an initial height H 0 ;
The cylindrical sample is made of a metal material to be tested according to the specification of a metal compression test method with the standard number of GB 7314-1987.
2) Compressing the cylindrical sample according to the regulation of a metal compression test method with the standard number of GB 7314-1987 to obtain a compressed sample of the cylinder, and measuring to obtain the height H of the compressed sample;
3) An axial view of the compressed sample is taken, and the minimum end face area A of the compressed sample in the axial view is identified by the image identification technology according to the following method t And a maximum cross-sectional area A m ;
3-1) converting the axial view of the compressed sample obtained by shooting into a gray image, and converting the gray image into a binary image;
for example, if the axial view of the compressed sample is a true color image, the method for converting the axial view of the compressed sample into a gray scale image is as follows:
3-1-1) calculating a weighted sum of the components of the true color patterns R, G, and B according to the following formula, and converting the RGB values into gray values:
I g =0.2989*R+0.5870*G+0.1140*B
in the formula I g The gray value of the gray image is obtained, R is an R channel component of the true color image, G is a G channel component of the true color image, and B is a B channel component of the true color image;
3-1-2) converting the axial view of the compressed sample into a gray scale image according to the calculated gray scale value.
3-2) obtaining a maximum cross section threshold value from the binary image by adopting a maximum inter-class variance method, and obtaining a minimum end face threshold value from the binary image by adopting an iterative threshold value method;
3-3) extracting a plurality of pixel points with the gray values of 0 in the binary image according to the maximum cross section threshold value to form the maximum cross section area A of the compressed sample m Actually, edge extraction is carried out on the binary image according to the gray characteristic of the binary image, the image is divided into a background part and a target part by adopting a maximum inter-class variance method, and the target part is selected as a maximum cross section area A of the compressed sample m ;
3-4) extracting a plurality of pixel points with the gray values of 0 from the binary image according to the minimum end face threshold value to form a minimum end face area A of the compressed sample t Similarly, the edge extraction is carried out on the binary image, the image is divided into a background part and a target part, and the target part is selected as the minimum end surface area A of the compressed sample t Only the parameters used in the edge extraction and the acquisition of the maximum cross-sectional area A m The time is different.
4) Respectively extracting the minimum end surface areas A t Maximum cross-sectional area A m Forming a boundary node matrix P of a minimum end face area t Boundary node matrix P of the maximum cross-sectional area m ;
The boundary information being the coordinates of points on the boundary lines of the regions, e.g. the maximum cross-sectional area A m Is the maximum cross-sectional area A m The set of coordinates of each point on the boundary line of (a).
5) Boundary node matrix P according to minimum end surface area t And boundary node matrix P of the maximum cross-sectional area m Respectively fitting a minimum end surface area circle and a maximum cross section area circle, and acquiring the radius of each circle;
the fitting method comprises a minimum containment region method, a minimum circumcircle method, a maximum inscribed circle method, a least square method and the like.
In general, in order to minimize the difference between the area of the fitted circle and the area of the original region, thereby reducing the error, the method is adoptedRespectively aligning boundary node matrixes P of minimum end surface areas by using a computer through a least square method t Boundary node matrix P of the maximum cross-sectional area m The data points in (3) are fitted to obtain a minimum end face area circle and a maximum cross section area circle.
6) The coefficient of friction during compression of the cylindrical sample was calculated according to the following formula:
where μ is the coefficient of friction during compression of the cylindrical sample, R t Radius of the circle of the smallest end surface area, R m Radius of the circle of maximum cross-sectional area, H is the height of the compressed sample, H 0 Is the initial height, R, of a cylindrical sample 0 Is the initial radius of the cylindrical sample.
Example 1 was carried out at room temperature using an aluminum alloy having a material designation of 6061:
1) According to the specification of a metal compression test method with the standard number of GB 7314-1987, after a metal material to be tested is manufactured into a cylindrical sample, the cylindrical sample is measured to obtain the initial radius R of the cylindrical sample 0 =4.98mm, initial height H of cylindrical sample 0 =9.96mm;
2) The cylindrical sample is then compressed under dry friction conditions according to the method of the metal compression test method of standard number GB 7314-1987: the forming speed is 0.1mms -1 The deformation is 50%, a compression sample of a cylinder is obtained by compression, and the height H =4.91mm of the compression sample is obtained by measurement;
3) An axial view of the compressed sample is taken, and the minimum end face area A of the compressed sample in the axial view is identified by the image identification technology according to the following method t And a maximum cross-sectional area A m ;
3-1) converting the axial view of the shot compressed sample into a gray image, and converting the gray image into a binary image;
for example, if the axial view of the compressed sample is a true color image, the method for converting the axial view of the compressed sample into a gray scale image is as follows:
3-1-1) calculating a weighted sum of the components of the true color patterns R, G, and B according to the following formula, and converting the RGB values into gray values:
I g =0.2989*R+0.5870*G+0.1140*B
in the formula I g The gray value of the gray image is obtained, R is an R channel component of the true color image, G is a G channel component of the true color image, and B is a B channel component of the true color image;
3-1-2) converting the axial view of the compressed sample into a gray scale image according to the calculated gray scale value.
3-2) obtaining a maximum cross section threshold value from the binary image by adopting a maximum inter-class variance method, and obtaining a minimum end face threshold value from the binary image by adopting an iterative threshold value method;
3-3) extracting a plurality of pixel points with the gray value of 0 in the binary image according to the maximum cross section threshold value to form the maximum cross section area A of the compressed sample m ;
3-4) extracting a plurality of pixel points with the gray value of 0 from the binary image according to the minimum end face threshold value to form a minimum end face area A of the compressed sample t 。
4) Respectively extracting the minimum end surface areas A t Maximum cross-sectional area A m Forming a boundary node matrix P of a minimum end face area t Boundary node matrix P of the maximum cross-sectional area m ;
The boundary information being the coordinates of points on the boundary lines of the regions, e.g. the maximum cross-sectional area A m Is the maximum cross-sectional area A m The set of coordinates of each point on the boundary line of (a).
5) Boundary node matrix P according to minimum end surface area t And boundary node matrix P of the maximum cross-sectional area m Respectively fitting the nodes in each boundary node matrix into corresponding circles by adopting a least square method, and acquiring the radius of each circle:
in this embodiment, the boundary of the minimum end face regionNode matrix P t The corresponding circle is a minimum end face area circle, and the radius of the minimum end face area circle is R t Boundary node matrix P of maximum cross-sectional area of =5.76mm m The corresponding circle is the circle of maximum cross-sectional area with radius R m =7.13mm;
6) The coefficient of friction during compression of the cylindrical sample was calculated according to the following formula:
where μ is the coefficient of friction during compression of the cylindrical sample, R t Radius of the circle of the smallest end face area, R m Radius of the largest cross-sectional area circle, H is the height of the compressed sample, H 0 Is the initial height, R, of a cylindrical sample 0 The initial radius of the cylindrical sample.
It was found from example 1 that the coefficient of friction μ of an aluminum alloy having a material designation of 6061 in a compression process under dry friction conditions at normal temperature was 0.31, and the test error under the same conditions as that of pin-and-disc friction test method of ASTM G99-04 was within 5%.
The aluminum alloy with the material mark of 6061 is adopted, and the method is carried out at the normal temperature according to the method of the invention as shown in the embodiment 2:
1) Preparing a metal material to be tested into a cylindrical sample according to the provisions of a metal compression test method with the standard number of GB 7314-1987, and measuring the cylindrical sample to obtain the initial radius R of the cylindrical sample 0 =4.99mm, initial height H of cylindrical sample 0 =9.97mm;
2) Then, the cylindrical sample is compressed in a boundary friction state according to the method in the metal compression test method with the standard number of GB 7314-1987: the forming speed is 0.1mms -1 Compressing to obtain a compressed sample of a cylinder, wherein the deformation is 50%, and measuring to obtain the height H =4.95mm of the compressed sample;
3) Taking an axial view of the compressed sampleThe minimum end surface area A of the compressed sample in the axial view is identified by adopting the image identification technology according to the following method t And a maximum cross-sectional area A m ;
3-1) converting the axial view of the compressed sample obtained by shooting into a gray image, and converting the gray image into a binary image;
for example, if the axial view of the compressed sample is a true color image, the method for converting the axial view of the compressed sample into a gray scale image is as follows:
3-1-1) calculating a weighted sum of the R, G and B components of the true color pattern, converting the RGB values to gray values according to the following formula:
I g =0.2989*R+0.5870*G+0.1140*B
in the formula I g The gray value of the gray image is obtained, R is an R channel component of the true color image, G is a G channel component of the true color image, and B is a B channel component of the true color image;
3-1-2) converting the axial view of the compressed sample into a gray scale image according to the calculated gray scale value.
3-2) obtaining a maximum cross section threshold value from the binary image by adopting a maximum inter-class variance method, and obtaining a minimum end face threshold value from the binary image by adopting an iterative threshold value method;
3-3) extracting a plurality of pixel points with the gray values of 0 in the binary image according to the maximum cross section threshold value to form the maximum cross section area A of the compressed sample m ;
3-4) extracting a plurality of pixel points with the gray values of 0 from the binary image according to the minimum end face threshold value to form a minimum end face area A of the compressed sample t 。
4) Respectively extracting the minimum end surface areas A t Maximum cross-sectional area A m Forming a boundary node matrix P of a minimum end face area t Boundary node matrix P of the maximum cross-sectional area m ;
The boundary information being the coordinates of points on the boundary line of the respective region, e.g. the maximum cross-sectional area A m Is the maximum cross-sectional area A m Each on the boundary line of (1)A set of coordinates of points.
5) Boundary node matrix P according to minimum end surface area t And boundary node matrix P of the maximum cross-sectional area m Respectively fitting the nodes in each boundary node matrix into corresponding circles by adopting a least square method, and acquiring the radius of each circle:
in this embodiment, the boundary node matrix P of the minimum end face area t The corresponding circle is a minimum end face area circle, and the radius of the minimum end face area circle is R t Boundary node matrix P of maximum cross-sectional area of =6.84mm m The corresponding circle is the maximum cross-sectional area circle with a radius R m =7.01mm;
6) The coefficient of friction during compression of the cylindrical sample was calculated according to the following formula:
where μ is the coefficient of friction during compression of the cylindrical sample, R t Radius of the circle of the smallest end face area, R m Radius of the circle of maximum cross-sectional area, H is the height of the compressed sample, H 0 Is the initial height, R, of a cylindrical sample 0 Is the initial radius of the cylindrical sample.
It was determined by example 2 that the coefficient of friction μ of an aluminum alloy having a material designation of 6061 in a compression process at room temperature under a boundary friction condition was 0.03, and the test error under the same condition as that of "Pin-on-disc Friction test method" having a Standard designation of ASTM G99-04 was within 5%.
Therefore, the error between the measurement results of the above embodiments 1 and 2 and the pin-disc friction test method is very small, which proves that the method has the advantages of simple steps, convenient use, easy implementation, strong reliability of the measurement result, high precision and conformity with the standard requirements.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and modifications of the present invention by those skilled in the art are within the scope of the present invention without departing from the spirit of the present invention.
Claims (7)
1. A method for measuring the friction coefficient of metal plastic forming by adopting an image recognition technology is characterized by comprising the following steps:
1) After a metal material to be measured is manufactured into a cylindrical sample, measuring the cylindrical sample to obtain initial radius and initial height data;
2) Compressing the cylindrical sample to obtain a compressed sample of the cylinder, and measuring to obtain height data of the compressed sample;
3) Shooting an axial view of a compressed sample, and identifying a minimum end surface area and a maximum cross section area of the compressed sample in the axial view by adopting an image identification technology;
4) Respectively extracting boundary information of the minimum end surface area and the maximum cross section area to form a boundary node matrix of the minimum end surface area and a boundary node matrix of the maximum cross section area;
5) Respectively fitting a minimum end face area circle and a maximum cross section area circle according to the boundary node matrix of the minimum end face area and the boundary node matrix of the maximum cross section area, and acquiring the radius of each circle;
6) The coefficient of friction during compression of the cylindrical sample was calculated according to the following formula:
where μ is the coefficient of friction during compression of the cylindrical sample, R t Radius of the circle of the smallest end face area, R m Radius of the largest cross-sectional area circle, H is the height of the compressed sample, H 0 Is the initial height, R, of the cylindrical sample 0 The initial radius of the cylindrical sample.
2. The method for determining the friction coefficient of metal plastic forming by adopting the image recognition technology as claimed in claim 1, wherein the cylindrical sample is made of the metal material to be measured according to the specification of the metal compression test method with the standard number of GB 7314-1987.
3. The method for determining the friction coefficient of metal plastic forming by image recognition technology as claimed in claim 1, wherein the compression sample is obtained by compressing a cylindrical sample according to the specification of the metal compression test method of the standard number GB 7314-1987.
4. The method for determining the friction coefficient of metal plastic forming by adopting the image recognition technology as claimed in claim 1, wherein the process of recognizing the axial view of the compression sample by adopting the image recognition technology is as follows:
3-1) converting the axial view of the compressed sample obtained by shooting into a gray image, and converting the gray image into a binary image;
3-2) obtaining a maximum cross section threshold value from the binary image by adopting a maximum inter-class variance method, and obtaining a minimum end face threshold value from the binary image by adopting an iterative threshold value method;
3-3) extracting a plurality of pixel points with the gray values of 0 in the binary image according to the maximum cross section threshold value to form a maximum cross section area of the compressed sample;
and 3-4) extracting a plurality of pixel points with the gray values of 0 from the binary image according to the minimum end face threshold value to form a minimum end face area of the compressed sample.
5. The method for determining the friction coefficient in plastic forming of metal using image recognition technology as claimed in claim 4, wherein if the axial view of the compressed sample is a true color image, the axial view of the compressed sample is converted into a gray scale image according to the following steps:
3-1-1) calculating a weighted sum of the R, G and B components of the true color pattern, converting the RGB values to gray values according to the following formula:
I g =0.2989*R+0.5870*G+0.1140*B
in the formula I g Is the gray value of the gray image, R is the true colorAn R channel component of the color image, G being a G channel component of the true color image, B being a B channel component of the true color image;
3-1-2) converting the axial view of the compressed sample into a gray scale image according to the calculated gray scale value.
6. The method for determining the friction coefficient of metal plastic forming by using the image recognition technology as claimed in claim 1, wherein the minimum end surface area circle and the maximum cross-sectional area circle are both obtained by least square fitting.
7. The method for determining the friction coefficient of metal plastic forming by image recognition technology as claimed in claim 1, wherein the boundary information is coordinates of each point on each regional boundary line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210897960.7A CN115308121A (en) | 2022-07-28 | 2022-07-28 | Method for measuring metal plastic forming friction coefficient by adopting image recognition technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210897960.7A CN115308121A (en) | 2022-07-28 | 2022-07-28 | Method for measuring metal plastic forming friction coefficient by adopting image recognition technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115308121A true CN115308121A (en) | 2022-11-08 |
Family
ID=83858676
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210897960.7A Pending CN115308121A (en) | 2022-07-28 | 2022-07-28 | Method for measuring metal plastic forming friction coefficient by adopting image recognition technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115308121A (en) |
-
2022
- 2022-07-28 CN CN202210897960.7A patent/CN115308121A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Buschhausen et al. | Evaluation of lubrication and friction in cold forging using a double backward-extrusion process | |
Dilmec et al. | Effect of geometrical and process parameters on coefficient of friction in deep drawing process at the flange and the radius regions | |
US6418795B2 (en) | Method of measuring shear friction factor through backward extrusion process | |
CN107655756B (en) | Paper elastic modulus testing method based on speckle printing | |
CN102539316A (en) | Method for measuring plastic-forming friction coefficient of magnesium alloy plate material | |
CN101619964A (en) | Quick microscopic detection method and quick microscopic detection device of micro accessory based on process match | |
CN103278445A (en) | Positive extrusion test method for plastic forming friction coefficient and friction factor | |
KR101763445B1 (en) | Method and system for generating tracing information for gas cylinders | |
CN115308121A (en) | Method for measuring metal plastic forming friction coefficient by adopting image recognition technology | |
CN109934231B (en) | Rod end face character image recognition method based on multi-direction gray level co-occurrence matrix | |
Male et al. | The relative validity of the concepts of coefficient of friction and interface friction shear factor for use in metal deformation studies | |
JPH057969A (en) | Method and device for evaluating performance of lubricator for forging | |
CN103760098B (en) | Based on the friction factor assay method of muscle ring compression deformation in band | |
CN106424259A (en) | Small-sized corrugated sheet folding device and method | |
CN110052539B (en) | Lubricant lubricating effect evaluation method used in stamping process | |
CN112504149A (en) | DIC technology-based method for obtaining sheet material hole expansion rate | |
CN210570392U (en) | Diameter-variable inspection device | |
Hari Krishna et al. | Effect of lubrication in cold upsetting using experimental and finite element modeling | |
CN112950765A (en) | Cavity straightness detection method based on point cloud modeling | |
CN111633116B (en) | Device and method for measuring and testing drawing height or bulging height of plate | |
CN114088617A (en) | Hot forging friction and lubrication effect optimization detection method | |
CN110633501A (en) | Method for determining bulging force energy parameters of ring rigid mold | |
CN112927185A (en) | True stress-true strain curve test calculation method based on digital image correlation method | |
CN103776989A (en) | Device and method for detecting conical forging lubricating effect | |
CN117900364B (en) | Near-net-shape forging method for offshore wind power tower flange |
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 |