CN112907556A - Automatic measuring method for abrasion loss of rotary cutter based on machine vision - Google Patents
Automatic measuring method for abrasion loss of rotary cutter based on machine vision Download PDFInfo
- Publication number
- CN112907556A CN112907556A CN202110266161.5A CN202110266161A CN112907556A CN 112907556 A CN112907556 A CN 112907556A CN 202110266161 A CN202110266161 A CN 202110266161A CN 112907556 A CN112907556 A CN 112907556A
- Authority
- CN
- China
- Prior art keywords
- image
- wear
- edge
- tool
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000005299 abrasion Methods 0.000 title abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000000691 measurement method Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- FASDKYOPVNHBLU-ZETCQYMHSA-N pramipexole Chemical compound C1[C@@H](NCCC)CCC2=C1SC(N)=N2 FASDKYOPVNHBLU-ZETCQYMHSA-N 0.000 claims 1
- 229960003089 pramipexole Drugs 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 11
- 238000003708 edge detection Methods 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000003754 machining Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06T7/0004—Industrial image inspection
-
- G06T5/70—
-
- G06T5/73—
-
- 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
Abstract
The invention provides a machine vision-based automatic measuring method for abrasion loss of a rotary cutter, which belongs to the technical field of machine vision measurement and is used for measuring the abrasion loss of the rotary cutter, and is characterized by comprising the following steps: step S1, collecting the image of the rotating rotary cutter by using an image collecting device; step S2, preprocessing the image, removing motion blur and other noises to obtain a preprocessed image; step S3, positioning the preprocessed image, and extracting the wear edge image of the rotary cutter; step S4, fitting sub-pixel edge points to the worn edge image through a main curve method to obtain a smooth edge image with a smooth edge curve; and step S5, calibrating the pixel equivalent by using the calibration plate, and calculating to obtain the actual maximum wear length of the rotary cutter.
Description
Technical Field
The invention belongs to the technical field of machine vision measurement, and particularly relates to a rotary cutter abrasion loss automatic measurement method based on machine vision.
Background
Machining is one of the main methods of machining at present, most parts are machined by tools, and particularly in the aviation manufacturing industry, an airplane needs millions of parts and hundreds of thousands of tools are consumed each year. The monitoring of the cutter state is a key problem of controlling the micro-working medium quantity of a part, the size precision of the part can be obviously reduced due to the excessive abrasion of the cutter and the abnormal cutter state, and the service life of the cutter is shortened. Research shows that the cutter wear monitoring technology can reduce the downtime caused by technological factors and human factors by 75 percent and improve the production efficiency by 10 to 50 percent. Tool wear is usually the most relevant parameter for tool performance testing, directly affecting final product quality, machine tool performance and tool life. The tool wear online monitoring can effectively avoid the scrapping of workpieces and improve the processing quality of products.
The methods for monitoring and measuring the wear of the tool mainly include direct measurement and indirect measurement. The change of the tool abrasion directly affects parameters such as cutting force, tool/workpiece vibration, acoustic emission signals, workpiece surface texture and the like. The indirect method judges the wear state of the tool by monitoring the changes of the parameters, but the detected signals contain a large number of interference factors which influence the detection of the result. The direct method is to directly monitor the wear state of the cutter, and currently, an optical instrument is mainly used for measuring the wear value of the cutter in production, so that the machine must be stopped for detection, the detection cost is increased, and the wear condition of the cutter is difficult to predict.
Machine vision measurement is used as a direct method, so that the contact interference of a measuring device on a tiny cutter can be avoided, and the progressive wear of the cutter can be directly measured for analysis. However, the existing tool wear visual measurement method can only be applied to the wear measurement of a specific tool, most of the existing tool wear visual measurement methods adopt an approximation method to fit the missing original boundary into a regular curve (a straight line, a circle or an ellipse), the tool wear condition cannot be truly reflected, and the existing tool wear visual measurement method cannot be widely applied to tools with complex wear shapes. Due to the complexity of the operation condition of the machine tool, the existing cutter wear visual measurement method needs to be stopped for detection in order to obtain a clear cutter image and shoot the cutter in a static state. Namely, the existing tool wear vision measurement method is difficult to accurately measure the wear of the rotary tool when the machine tool runs, and the error of reconstructing the missing original boundary by adopting an approximation method is large.
Disclosure of Invention
In order to solve the problems, the invention provides a method for automatically measuring the abrasion loss of a rotary cutter based on machine vision, which adopts the following technical scheme:
the invention provides a machine vision-based automatic measuring method for abrasion loss of a rotary cutter, which is used for measuring the abrasion loss of the rotary cutter and is characterized by comprising the following steps: step S1, collecting the image of the rotating rotary cutter by using an image collecting device; step S2, preprocessing the image, removing motion blur and other noises to obtain a preprocessed image; step S3, positioning the preprocessed image, and extracting the wear edge image of the rotary cutter; step S4, fitting sub-pixel edge points to the worn edge image through a main curve method to obtain a smooth edge image with a smooth edge curve; and step S5, calibrating the pixel equivalent by using the calibration plate, and calculating to obtain the actual maximum wear length of the rotary cutter.
The automatic measuring method for the wear amount of the rotary tool based on the machine vision provided by the invention can also have the following characteristics, wherein the step S3 comprises the following steps: step S3-1, performing threshold segmentation on the preprocessed image to obtain a threshold segmentation image; step S3-2, processing the threshold segmentation image through morphological operation to obtain a refined image; step S3-3, performing edge rough positioning on the refined image by using a Canny operator to obtain a rough positioning edge image; step S3-4, carrying out image registration on the rough positioning edge image of the rotary tool and the edge image of the reference tool, and extracting a wear area; and step S3-5, precisely positioning the wear edge of the rotary tool by using a sub-pixel edge method based on Zernike moments on the wear area to obtain a wear edge image.
The automatic measuring method of the wear amount of the rotary tool based on the machine vision provided by the invention can also have the characteristic that in the step S3-4, the edge image of the reference tool and the rough positioning edge image of the rotary tool are subjected to a projection method to obtain image characteristic points, and then the rough positioning edge image of the rotary tool and the edge image of the reference tool are fused to extract a wear area.
The automatic measuring method for the abrasion loss of the rotary cutter based on the machine vision can also be characterized in that the projection method comprises the following steps: step T1, reading the rough positioning edge image and carrying out graying to obtain a gray value, a pixel row number and a pixel column number; step T2, drawing vertical projection and horizontal projection of the rough positioning edge image according to the gray value, the pixel row number and the pixel column number of the rough positioning edge image; and step T3, determining the position of the feature point of the image through the vertical projection and the horizontal projection of the rough positioning edge image.
The automatic measuring method for the abrasion loss of the rotary tool based on the machine vision can also have the characteristic that in the step S3-5, the sub-pixel edge method based on the Zernike moment has an adaptive step gray threshold.
The automatic measuring method for the wear of the rotary tool based on the machine vision, provided by the invention, can also have the characteristic that in the step S3-1, the maximum inter-class variance method improved by the edge information of the Prasiian is adopted to carry out threshold segmentation.
The method for automatically measuring the wear amount of the rotary tool based on the machine vision may further have a feature in that, in step S1, the rotary tool rotates at a fixed low rotation speed, and the image capturing device includes a camera, a three-color spherical light source, a camera holder, and a computer.
The machine vision-based automatic measuring method for the wear amount of the rotary tool may further have a feature in which, in step S2, the preprocessing includes removing motion blur using wiener filtering, enhancing the wear region of the rotary tool using piecewise linear transformation, and removing noise using an adaptive median filtering method.
The automatic measuring method for the abrasion loss of the rotary cutter based on the machine vision can also have the characteristic that the calibration plate is a chessboard calibration plate.
The method for automatically measuring the wear amount of the rotary tool based on the machine vision may further include the step of obtaining the number of pixels n occupied by each cell of the calibration plate by performing focus photographing on the calibration plate in step S5, wherein when the actual size of each cell of the calibration plate is l, the pixel equivalent is k ═ l/n.
Action and Effect of the invention
According to the invention, the automatic wear measurement method of the rotary tool based on machine vision is used for measuring the wear of the rotary tool, and comprises the following steps: collecting an image of the rotating rotary tool using an image collection device; preprocessing the image, and removing motion blur to obtain a preprocessed image; positioning the preprocessed image, and extracting a wear edge image of the rotary cutter; fitting sub-pixel edge points to the wear edge image by a main curve method to obtain a smooth edge image with a smooth edge curve; and calibrating the pixel equivalent by using the calibration plate and obtaining the actual maximum wear length of the rotary cutter. The automatic measuring method for the abrasion loss of the rotary cutter can measure the abrasion loss of the cutter with a complex shape and obtain a relatively accurate result, can monitor the rotary cutter in real time, effectively avoids scrapping of workpieces and improves the processing quality of products. The embodiment uses the nonlinear fitting method of the sub-pixel coordinate points based on the main curve fitting method, and can be further suitable for tool wear calculation with complicated wear shapes.
Drawings
FIG. 1 is a flow chart of a method for automatic measurement of wear of a rotary cutter according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention;
FIG. 3 is a graph of the results of image preprocessing and image segmentation for a reference tool according to an embodiment of the present invention;
FIG. 4 is a diagram of the results of image preprocessing and image segmentation for a rotating tool according to an embodiment of the present invention;
FIG. 5 shows the results of rough positioning and worn region extraction for edge detection of a tool image according to an embodiment of the present invention;
FIG. 6 shows the tool image sub-pixel edge detection and master curve fitting results in an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings.
< example >
The embodiment provides a machine vision-based automatic wear measurement method for a rotary tool, which is used for measuring and monitoring the wear of the rotary tool in real time.
Fig. 1 is a flowchart of a method for automatically measuring a wear amount of a rotary cutter according to an embodiment of the present invention.
The method for automatically measuring the wear amount of the rotary tool based on machine vision according to the present embodiment is described below with reference to fig. 1.
Step S1, an image of the rotating rotary tool is captured using the image capture device.
Fig. 2 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention.
As shown in fig. 2, in the present embodiment, the image capturing device 100 includes a camera 1, a three-color annular light source 2, a camera holder (not shown in the figure), and a computer 4. In this embodiment, the camera 1 is a CMOS industrial area-array camera.
The rotary cutter 200 is fixed by a jig 300 of the numerical control machine tool, and the rotary cutter 200 is controlled by the numerical control machine tool to rotate at a fixed low rotation speed. In this embodiment, the fixed low rotation speed is in the range of 10n/mim to 20 n/min.
In this embodiment, the image capturing device 100 is disposed below the rotary cutter 200, specifically, the three-color annular light source 2 is disposed below the rotary cutter 200 in the horizontal direction, and the light path of the light source passes through the rotation axis of the rotary cutter 200, and the CMOS industrial area-array camera 1 is disposed below the three-color annular light source 2 and fixed on the worktable 3 by a camera holder.
Fig. 3 is a diagram showing the result of image preprocessing and image segmentation of the reference tool according to the embodiment of the present invention, and fig. 4 is a diagram showing the result of image preprocessing and image segmentation of the rotating tool (worn tool) according to the embodiment of the present invention.
The image acquisition device 100 acquires an image of a reference tool, i.e., a standard new tool, and a tool image of a rotating tool 200, i.e., a tool image of each wear stage of a worn tool, as shown in fig. 3 and 4, due to the influence of tool surface texture and illumination, a clear profile of the tool cannot be obtained by directly performing image segmentation, and the segmented image has problems of tool profile loss, many holes, and the like.
And step S2, preprocessing the image acquired in the step S1, removing motion blur and noise reduction interference in the image, and obtaining a preprocessed image.
In this embodiment, as shown in fig. 3, the image preprocessing includes wiener filtering to remove motion blur, piecewise linear gray scale transformation to enhance the tool wear region, and adaptive median filtering to remove the noise-smoothed image.
And step S3, positioning the preprocessed image and extracting the wear edge image of the rotary cutter.
In this embodiment, in step S3, the image is subjected to threshold segmentation, morphological operation, Canny operator edge detection coarse positioning, image registration, and Zernike moment method sub-pixel edge fine positioning to extract the tool wear edge, and then a main curve method is used to fit sub-pixel edge points to obtain a smooth edge image with a smooth edge curve.
Specifically, step S3 includes the steps of:
and step S3-1, performing threshold segmentation on the preprocessed image to obtain a threshold segmentation image.
Specifically, as shown in fig. 3, the threshold segmentation is performed by the maximum inter-class variance method improved by edge information.
And step S3-2, processing the threshold segmentation image through morphological operation to obtain a refined image.
And step S3-3, performing edge rough positioning on the refined image by using a Canny operator to obtain a rough positioning edge image.
Specifically, after deburring and thinning through morphological operations such as corrosion and expansion, edge rough positioning is carried out by using a Canny operator.
Step S3-4, image registration is performed on the roughly positioned edge image of the rotating tool and the edge image of the reference tool, as shown in fig. 4, and the wear region is extracted.
Specifically, image feature points are quickly found from edge images of a reference cutter and a worn cutter through a projection method, then image registration is carried out, the edge images of the worn cutter and the edge images of a standard cutter are fused, and a worn area is extracted.
FIG. 5 shows the tool image edge detection coarse positioning and worn region extraction results in an embodiment of the present invention.
As shown in fig. 5, Canny operator edge detection is performed on the segmented images of the unworn tool image and the worn tool image before drilling, respectively, to obtain edges at a single pixel level. And finally, acquiring an image characteristic point by a projection method, registering the two edge images, and extracting a wear region through operations such as rotation, translation and the like.
The projection method comprises the following specific steps:
step T1, reading an image f (x, y), namely, roughly positioning an edge image, graying to obtain a gray image, namely, obtaining a gray value, and obtaining the number m of pixel rows and the number n of pixel columns;
step T2, calculating the sum of the gray values of each row of pixels of the image f (x, y), storing the sum of the gray values in an array A, and drawing an image of the sum of the gray values with respect to the row number n of pixels, namely vertical projection; similarly, calculating the sum of the gray values of the pixels on each row of the image f (x, y), storing the sum of the gray values into an array B, and drawing an image of the sum of the gray values and the row number m of the pixels, namely horizontal projection;
at step T3, the image feature point positions are determined by the vertical projection and the horizontal projection of the image f (x, y).
And step S3-5, precisely positioning the wear edge of the rotary tool by using a sub-pixel edge method based on Zernike moments on the wear area to obtain a wear edge image.
The sub-pixel edge method based on the Zernike moment has a self-adaptive step gray threshold, namely, the inter-class variance of pixel step gray values of a target area and a background area of a rotary cutter image is taken as a target function, the step gray value of each pixel takes the maximum value of the difference between the pixel and the gray values of pixels in eight neighborhoods of the pixel, and the step gray value with the maximum inter-class variance is taken as the self-adaptive selected step gray threshold by utilizing the principle of an Otsu threshold method.
Step S4, sub-pixel edge points are fitted to the worn edge image by the master curve method, as shown in fig. 5, resulting in a smooth edge image with a smooth edge curve.
FIG. 6 shows the tool image sub-pixel edge detection and master curve fitting results in an embodiment of the invention.
In order to improve the measurement precision to a sub-pixel level, edge points are detected by adopting a Zernike moment sub-pixel edge detection method and the sub-pixel edge points are fitted by adopting a main curve method. The Zernike moment sub-pixel edge detection method reserves effective information, can obtain clear abrasion profiles, has small calculated amount, is insensitive to noise and has high accuracy. The sub-pixel edge detection algorithm based on the Zernike moment has less calculation time while ensuring the precision, and is more suitable for the online measurement of the tool wear. As shown in fig. 6, finally, curve fitting is performed on the sub-pixel coordinate points obtained in the sub-pixel edge detection step by using a main curve method, fitting of the wear boundary of the complex shape can be completed by fitting the discrete points by using the main curve method, and the tool is more applicable and has a wider application range.
Step S5, keeping the object distance of the camera 1 unchanged, obtaining the pixel equivalent of the camera 1 at the object distance by using the calibration board, that is, the actual physical length represented by each pixel on the image captured by the camera at the object distance, and multiplying the pixel equivalent by the pixel number occupied by the maximum wear width of the rotary tool to obtain the actual maximum wear length of the rotary tool.
In this embodiment, the calibration board is a checkerboard calibration board, and the specific process of calibrating the pixel equivalent is as follows: the camera 1 is used for focusing and photographing the calibration plate to obtain the number of pixels n occupied by each small cell of the calibration plate, and if the actual size of each small cell of the calibration plate is l, the pixel equivalent is k ═ l/n.
Examples effects and effects
The embodiment provides a machine vision-based automatic measuring method for the abrasion loss of a rotary tool, which is used for measuring the abrasion loss of the rotary tool and comprises the following steps: collecting an image of the rotating rotary tool using an image collection device; preprocessing the image, and removing motion blur to obtain a preprocessed image; positioning the preprocessed image, and extracting a wear edge image of the rotary cutter; fitting sub-pixel edge points to the wear edge image by a main curve method to obtain a smooth edge image with a smooth edge curve; and calibrating the pixel equivalent by using the calibration plate and obtaining the actual maximum wear length of the rotary cutter. The automatic measuring method for the abrasion loss of the rotary cutter can measure the abrasion loss of the cutter with a complex shape and obtain a relatively accurate result, can monitor the rotary cutter in real time, effectively avoids scrapping of workpieces and improves the processing quality of products. The embodiment uses the nonlinear fitting method of the sub-pixel coordinate points based on the main curve fitting method, and can be further suitable for tool wear calculation with complicated wear shapes.
The automatic measuring method for the abrasion loss of the rotary cutter based on the machine vision uses the method for removing the motion blur by the wiener filter, can effectively remove the motion blur effect of the image of the rotary cutter, and provides a new idea for dynamic vision measurement.
The automatic measuring method for the wear loss of the rotary cutter based on the machine vision obtains the feature points through the projection method to perform image registration, so that the reconstruction of the original boundary of the cutter is realized, a more real wear area is obtained, and the measuring precision is improved.
The automatic measuring method for the abrasion loss of the rotary cutter based on the machine vision can find accurate characteristic points through a projection method, improves the speed of detecting the characteristic points, and is suitable for online measurement with high requirement on the running speed.
The automatic measuring method for the abrasion loss of the rotary cutter based on the machine vision uses a Zernike moment subpixel detecting method for adaptively determining the condition of the threshold value of the step gray scale, avoids the manual selection of the threshold value of the step gray scale, and realizes the accurate positioning of the abrasion edge of the cutter.
The above-described embodiments are merely illustrative of specific embodiments of the present invention, and the present invention is not limited to the description of the above-described embodiments.
Claims (10)
1. A rotary tool wear amount automatic measurement method based on machine vision is used for measuring the wear amount of a rotary tool, and is characterized by comprising the following steps:
step S1, collecting the image of the rotating tool by using an image collecting device;
step S2, preprocessing the image, removing motion blur and other noises to obtain a preprocessed image;
step S3, processing the pre-processed image, and extracting a wear edge image of the rotary cutter;
step S4, fitting sub-pixel edge points to the wear edge image through a main curve method to obtain a smooth edge image with a smooth edge curve;
and step S5, calibrating the pixel equivalent by using a calibration plate, and calculating to obtain the actual maximum wear length of the rotary cutter.
2. The machine-vision-based automatic rotary tool wear measurement method of claim 1, wherein the step S3 includes the steps of:
step S3-1, performing threshold segmentation on the preprocessed image to obtain a threshold segmentation image;
step S3-2, processing the threshold segmentation image through morphological operation to obtain a refined image;
step S3-3, performing edge rough positioning on the refined image by using a Canny operator to obtain a rough positioning edge image;
step S3-4, carrying out image registration on the rough positioning edge image of the rotating tool and the edge image of the reference tool, and extracting a wear area;
and step S3-5, precisely positioning the wear edge of the rotary tool by using a sub-pixel edge method based on Zernike moments on the wear area to obtain a wear edge image.
3. The machine-vision-based automatic rotary tool wear measurement method of claim 2, wherein:
in step S3-4, image feature points are obtained from the edge image of the reference tool and the rough positioning edge image of the rotating tool by a projection method, and the rough positioning edge image of the rotating tool and the edge image of the reference tool are fused to extract the wear region.
4. The machine-vision-based automatic rotary tool wear measurement method of claim 3, wherein:
wherein the projection method comprises the following steps:
step T1, reading the rough positioning edge image and carrying out graying to obtain a gray value, a pixel row number and a pixel column number;
step T2, drawing a vertical projection and a horizontal projection of the rough positioning edge image according to the gray value, the pixel row number and the pixel column number of the rough positioning edge image;
and step T3, determining the position of the image feature point through the vertical projection and the horizontal projection of the coarse positioning edge image.
5. The machine-vision-based automatic rotary tool wear measurement method of claim 2, wherein:
in step S3-5, the Zernike moment-based sub-pixel edge method has an adaptive step gray threshold.
6. The machine-vision-based automatic rotary tool wear measurement method of claim 2, wherein:
in step S3-1, threshold segmentation is performed by using a variance method between maximum classes improved by edge information of the pramipexole operator.
7. The machine-vision-based automatic rotary tool wear measurement method of claim 1, wherein:
wherein in the step S1, the rotary cutter rotates at a fixed low rotation speed,
the range of the fixed low rotating speed is 10 n/min-20 n/min,
the image acquisition device comprises a camera, a three-color spherical light source, a camera support and a computer.
8. The machine-vision-based automatic rotary tool wear measurement method of claim 1, wherein:
wherein, in the step S2, the preprocessing includes removing the motion blur using wiener filtering, enhancing a wear region of the rotating tool using piecewise linear transformation, and removing noise using an adaptive median filtering method.
9. The machine-vision-based automatic rotary tool wear measurement method of claim 1, wherein:
wherein the calibration plate is a chessboard calibration plate.
10. The machine-vision-based automatic rotary tool wear measurement method of claim 1, wherein:
in step S5, the calibration board is photographed in focus to obtain the number of pixels n occupied by each cell of the calibration board, and if the actual size of each cell of the calibration board is l, the pixel equivalent is k ═ l/n.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110266161.5A CN112907556A (en) | 2021-03-11 | 2021-03-11 | Automatic measuring method for abrasion loss of rotary cutter based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110266161.5A CN112907556A (en) | 2021-03-11 | 2021-03-11 | Automatic measuring method for abrasion loss of rotary cutter based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112907556A true CN112907556A (en) | 2021-06-04 |
Family
ID=76105653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110266161.5A Pending CN112907556A (en) | 2021-03-11 | 2021-03-11 | Automatic measuring method for abrasion loss of rotary cutter based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907556A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221058A (en) * | 2021-06-08 | 2021-08-06 | 中国科学院软件研究所 | Method for detecting and evaluating abrasion loss of outer edge of circular fitting |
| CN113269766A (en) * | 2021-06-07 | 2021-08-17 | 中铁工程装备集团有限公司 | Hob abrasion detection method, hob abrasion detection device, hob abrasion detection equipment and readable storage medium |
| CN114850967A (en) * | 2022-04-18 | 2022-08-05 | 上海交通大学 | Cutter wear state detection method and system based on human-in-loop |
| CN115008255A (en) * | 2022-08-09 | 2022-09-06 | 南通吉帆精密科技有限公司 | Tool wear identification method and device for machine tool |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105758862A (en) * | 2016-01-26 | 2016-07-13 | 西安交通大学 | Online oxidative wear state monitoring method based on color extraction of wear particle image |
| CN111230593A (en) * | 2020-03-02 | 2020-06-05 | 西南交通大学 | Milling cutter abrasion loss visual measurement method based on dynamic image sequence |
| CN111692969A (en) * | 2020-07-27 | 2020-09-22 | 上海威研精密科技有限公司 | Cutter bounce on-machine vision detector and detection method thereof |
-
2021
- 2021-03-11 CN CN202110266161.5A patent/CN112907556A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105758862A (en) * | 2016-01-26 | 2016-07-13 | 西安交通大学 | Online oxidative wear state monitoring method based on color extraction of wear particle image |
| CN111230593A (en) * | 2020-03-02 | 2020-06-05 | 西南交通大学 | Milling cutter abrasion loss visual measurement method based on dynamic image sequence |
| CN111692969A (en) * | 2020-07-27 | 2020-09-22 | 上海威研精密科技有限公司 | Cutter bounce on-machine vision detector and detection method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 周俊杰等: "基于机器视觉的加工刀具磨损量在线测量", 《上海交通大学学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269766A (en) * | 2021-06-07 | 2021-08-17 | 中铁工程装备集团有限公司 | Hob abrasion detection method, hob abrasion detection device, hob abrasion detection equipment and readable storage medium |
| CN113221058A (en) * | 2021-06-08 | 2021-08-06 | 中国科学院软件研究所 | Method for detecting and evaluating abrasion loss of outer edge of circular fitting |
| CN113221058B (en) * | 2021-06-08 | 2022-05-10 | 中国科学院软件研究所 | Method for detecting and evaluating abrasion loss of outer edge of circular accessory |
| CN114850967A (en) * | 2022-04-18 | 2022-08-05 | 上海交通大学 | Cutter wear state detection method and system based on human-in-loop |
| CN114850967B (en) * | 2022-04-18 | 2024-04-19 | 上海交通大学 | Method and system for detecting cutter abrasion state based on man-in-loop |
| CN115008255A (en) * | 2022-08-09 | 2022-09-06 | 南通吉帆精密科技有限公司 | Tool wear identification method and device for machine tool |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112907556A (en) | Automatic measuring method for abrasion loss of rotary cutter based on machine vision | |
| Dai et al. | A machine vision system for micro-milling tool condition monitoring | |
| Su et al. | An automated flank wear measurement of microdrills using machine vision | |
| Kumar et al. | Machine vision method for non-contact measurement of surface roughness of a rotating workpiece | |
| Peng et al. | Study of tool wear monitoring using machine vision | |
| CN102496161B (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| Bradley et al. | Surface texture indicators of tool wear-a machine vision approach | |
| CN110146019B (en) | Workpiece size online detection and automatic compensation method based on industrial camera | |
| Shahabi et al. | In-cycle monitoring of tool nose wear and surface roughness of turned parts using machine vision | |
| Zhang et al. | Research on tool wear detection based on machine vision in end milling process | |
| CN111230593A (en) | Milling cutter abrasion loss visual measurement method based on dynamic image sequence | |
| Peng et al. | Application of machine vision method in tool wear monitoring | |
| CN110091217B (en) | Turning flutter acceleration acquisition system and method based on machine vision | |
| CN113592955B (en) | Round workpiece plane coordinate high-precision positioning method based on machine vision | |
| CN102441581A (en) | Machine vision-based device and method for online detection of structural steel section size | |
| Zhou et al. | Chisel edge wear measurement of high-speed steel twist drills based on machine vision | |
| CN113870217A (en) | Edge deviation vision measurement method based on machine vision and image detector | |
| CN113222955A (en) | Gear size parameter automatic measurement method based on machine vision | |
| Bagga et al. | A novel approach of combined edge detection and segmentation for tool wear measurement in machining | |
| CN114581805A (en) | Coating roller surface defect detection method adopting 3D line laser profile technology | |
| CN105184792B (en) | A kind of saw blade wear extent On-line Measuring Method | |
| CN116539620A (en) | On-machine detection method for surface defects of cutter | |
| CN112489042A (en) | Metal product printing defect and surface damage detection method based on super-resolution reconstruction | |
| Shahabi et al. | On-line monitoring of tool wear in turning operation in the presence of tool misalignment | |
| Póka et al. | A robust digital image processing method for measuring the planar burr length at milling |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210604 |
|
| WD01 | Invention patent application deemed withdrawn after publication |