CN113134791A - Workpiece surface treatment method based on image recognition and shot blasting machine - Google Patents

Workpiece surface treatment method based on image recognition and shot blasting machine Download PDF

Info

Publication number
CN113134791A
CN113134791A CN202110480127.8A CN202110480127A CN113134791A CN 113134791 A CN113134791 A CN 113134791A CN 202110480127 A CN202110480127 A CN 202110480127A CN 113134791 A CN113134791 A CN 113134791A
Authority
CN
China
Prior art keywords
shot blasting
image
processing module
gray
workpiece
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
CN202110480127.8A
Other languages
Chinese (zh)
Inventor
李小凡
李慧媛
姚金泽
张兰红
何佳昊
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.)
Yancheng Institute of Technology
Original Assignee
Yancheng Institute of Technology
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 Yancheng Institute of Technology filed Critical Yancheng Institute of Technology
Priority to CN202110480127.8A priority Critical patent/CN113134791A/en
Publication of CN113134791A publication Critical patent/CN113134791A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24C—ABRASIVE OR RELATED BLASTING WITH PARTICULATE MATERIAL
    • B24C1/00—Methods for use of abrasive blasting for producing particular effects; Use of auxiliary equipment in connection with such methods
    • B24C1/08—Methods for use of abrasive blasting for producing particular effects; Use of auxiliary equipment in connection with such methods for polishing surfaces, e.g. smoothing a surface by making use of liquid-borne abrasives
    • B24C1/086—Descaling; Removing coating films
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24C—ABRASIVE OR RELATED BLASTING WITH PARTICULATE MATERIAL
    • B24C3/00—Abrasive blasting machines or devices; Plants
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24C—ABRASIVE OR RELATED BLASTING WITH PARTICULATE MATERIAL
    • B24C9/00—Appurtenances of abrasive blasting machines or devices, e.g. working chambers, arrangements for handling used abrasive material
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24C—ABRASIVE OR RELATED BLASTING WITH PARTICULATE MATERIAL
    • B24C9/00—Appurtenances of abrasive blasting machines or devices, e.g. working chambers, arrangements for handling used abrasive material
    • B24C9/003—Removing abrasive powder out of the blasting machine
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes

Abstract

The invention discloses a workpiece surface treatment method based on image recognition and a shot blasting machine, and relates to the field of shot blasting machines. The shot blasting machine comprises a shot blasting device, a translation device, a camera device, an image processing module and a control unit. After the shot blasting device processes a workpiece, the image pickup device shoots an image and transmits the shot image to the image processing module, the image processing module converts the image into a gray image, and identifies defect points according to gray values of pixel points on the gray image and generates identification information, and the identification information comprises: the control unit judges whether the processing is qualified or not according to the identification information and controls the shot blasting device and the translation device to carry out secondary processing on unqualified workpieces. The invention can effectively improve the shot blasting treatment effect, avoid the process of repeatedly putting the machine on the machine due to unqualified workpieces and save the working time.

Description

Workpiece surface treatment method based on image recognition and shot blasting machine
Technical Field
The invention relates to the field of shot blasting machines, in particular to a workpiece surface processing method based on image recognition and a shot blasting machine.
Background
The shot blasting treatment is a process for effectively removing flaws such as oxide skin, rust and the like on the surface of a metal workpiece, when the surface of the workpiece is treated by the conventional shot blasting machine, the working time of the shot blasting machine is usually set to be fixed in advance or set according to an empirical value, and the shot blasting machine stops working after the set working time is finished. The effect of workpiece processing lacks the process of machine detection, and if the situation of incomplete processing exists, the workpiece needs to be repeatedly operated, which wastes time.
Disclosure of Invention
The invention aims to provide a workpiece surface treatment method based on image recognition to solve the problems, and the method is applied to a shot blasting machine and is characterized in that: the shot blasting machine comprises a shot blasting device, a translation device, a camera device, an image processing module and a control unit;
the translation device drives the shot blasting devices to move on the same horizontal plane;
the camera device is used for shooting a workpiece and transmitting a shot image to the image processing module;
the image processing module is used for identifying and processing the information in the image to obtain identification information;
the control unit generates a control signal according to the identification information so as to control the shot blasting device, the translation device, the camera device and the image processing module to work cooperatively;
the method for processing the surface of the workpiece comprises the following specific steps:
and B: placing a workpiece to be processed under a shot blasting device, and starting a shot blasting machine to perform rough machining on the workpiece to be processed;
and C: starting a camera device to acquire an image of the roughly machined workpiece, and transmitting the image to the image processing module, wherein the image processing module converts the image into a gray image, and the gray value of each pixel point on the gray image is alpha;
step D: the image processing module counts the number of total pixel points in the gray level image to be N;
step E: setting a gray threshold T, when the gray value of a pixel point meets alpha < T, judging the pixel point as a defective pixel point by an image processing module, and counting the number of the defective pixel points as n by the image processing module;
step F: the control unit calculates the proportion theta of the flaw area to the workpiece area, and the theta is N/N, and sets a standard value thetamE.g. theta ≦ thetamJudging to be qualified, and finishing shot blasting work; e.g. theta > thetamIf the judgment result is unqualified, continuing to execute the step G;
step G: the image processing module picks up the coordinates of the flaw points and sends the coordinates of the flaw points to the control unit, the control unit controls the translation device to drive the shot blasting device to move to the coordinates of each flaw point, finish machining shot blasting is carried out, and the step C is returned to and continuously executed after finishing;
wherein the standard value θmIs the expected value of the surface treatment effect of the workpiece.
Further, in the step C, the image processing module converts the collected image into a gray scale image by using Gamma correction, where the gray scale value α satisfies:
Figure BDA0003048874050000031
r, G, B represents the color value of the corresponding color of each pixel point in the collected image.
Further, the standard value θm＝0.01。
Further, the method also comprises the following step A: the camera device shoots a standard workpiece to generate a standard diagramThe image processing module converts the standard pattern into a standard gray image and generates a gray histogram, wherein a gray value corresponding to a peak value in the gray histogram is alphahAnd E, setting the gray threshold T in the step E to meet the following conditions:
T＝αh-20。
in order to realize the method, the invention also discloses a shot blasting machine, which comprises the following steps: a shot blasting chamber;
the shot blasting device comprises a shot blasting device and a shot conveying pipeline;
the translation device is arranged in the shot blasting chamber, the shot blasting device is arranged in the translation device, and the translation device is used for driving the shot blasting devices to move on the same horizontal plane;
the camera device is arranged at the top of the shot blasting chamber and used for shooting a workpiece and transmitting a shot image to the image processing module;
the image processing module is configured to convert the captured image into a grayscale image, identify a defective point according to a grayscale value of a pixel point on the grayscale image, and generate identification information, where the identification information includes: the number of defective pixel points, the total number of the gray image pixel points and the coordinates of the defective pixel points;
and the control unit generates a control signal according to the identification information so as to control the shot blasting device, the translation device, the camera device and the image processing module to work cooperatively.
Furthermore, the camera device is arranged at the center of the top of the shot blasting chamber and used for obtaining a better image shooting effect.
Further, the shot blasting machine further comprises a light source device, and the light source device is installed at the top of the shot blasting chamber.
Further, the shot blasting machine further comprises an air supply device, the air supply device comprises an air box and a fan arranged in the air box, the air box is provided with an air outlet, and a grid is arranged on the air outlet. The air supply device is used for removing shot blasting, impurities or dust left on the surface of the workpiece after shot blasting treatment.
Has the advantages that:
compared with shot blasting equipment in the prior art, the shot blasting machine using the method and the method disclosed by the invention can judge whether the processing of the workpiece reaches the standard or not through an image detection method after the workpiece is processed. The shot blasting equipment can be automatically controlled to perform secondary processing aiming at the unqualified area, so that the shot blasting processing effect is further improved, the process of repeatedly operating the machine due to unqualified workpieces is avoided, and the working time is saved.
Drawings
FIG. 1 is a flow chart of a method for processing a surface of a workpiece based on image recognition according to the present invention;
FIG. 2 is a gray level histogram generated in step A of FIG. 1;
FIG. 3 is a schematic structural diagram of a shot blasting machine according to the present invention;
FIG. 4 is a schematic view of the internal structure of a shot blasting machine according to the present invention;
FIG. 5 is a schematic view of the shot blasting chamber of FIG. 4 with the shot blasting chamber removed;
fig. 6 is a schematic structural diagram of a preferred air supply device.
Wherein: 1-shot blasting chamber; 2-shot blasting device; 21-a shot blasting machine; 22-pill delivery pipe; 3-a translation device; 31-a slide bar; 32-a slider; 4-a camera device; 5-an image processing module; 6-a control unit; 7-a workpiece; 8-a light source device; 9-an air supply device; 91-air box; 92-a fan; 93-grid.
Detailed Description
The invention discloses a workpiece surface processing method based on image recognition, which is applied to a shot blasting machine and aims to recognize the processing condition of surface flaws of a workpiece after the workpiece is primarily processed by the shot blasting machine and determine whether secondary processing is needed or not according to a recognition result. The scale can be rust spots on the surface of the metal workpiece. The method can significantly improve the treatment effect and efficiency, and the embodiment is further described with reference to the accompanying drawings:
as shown in fig. 1, a workpiece surface processing method based on image recognition is applied to a shot blasting machine, and the shot blasting machine comprises a shot blasting device, a translation device, a camera device, an image processing module and a control unit;
the translation device drives the shot blasting devices to move on the same horizontal plane;
the image pickup device is used for shooting a workpiece and transmitting a shot image to the image processing module;
the image processing module is used for identifying information in the image;
and the control unit generates a control signal according to the identification information so as to control the shot blasting device, the translation device, the camera device and the image processing module to work cooperatively.
The method mainly comprises the following steps:
and B: placing a workpiece to be processed under a shot blasting device, and starting a shot blasting machine to perform rough machining on the workpiece to be processed;
and C: starting a camera device to acquire an image of the roughly machined workpiece, and transmitting the image to the image processing module, wherein the image processing module converts the image into a gray image, and the gray value of each pixel point on the gray image is alpha;
step D: the image processing module counts the number of total pixel points in the gray level image to be N;
step E: setting a gray threshold T, when the gray value of a pixel point meets the condition that alpha is less than T, the pixel point is a defective pixel point, and the image processing module counts the number of the defective pixel points to be n;
step F: the control unit calculates the proportion theta of the flaw area to the workpiece area, and the theta is N/N, and sets a standard value thetamE.g. theta ≦ thetamJudging to be qualified, and finishing shot blasting work; e.g. theta > thetamIf the judgment result is unqualified, continuing to execute the step G;
step G: and the image processing module picks up the coordinates of the flaw points and sends the coordinates of the flaw points to the control unit, the control unit controls the translation device to drive the shot blasting device to move to the coordinates of each flaw point, finish machining shot blasting is carried out, and after finishing, the step C is returned to and continuously executed. Obviously, after step G is completed and before step C is performed, the translating device should translate the shot-blasting device to a position where there is no interference with image acquisition.
And B, in the rough machining process, driving the shot blasting device to perform shot blasting by the translation device. In order to meet workpieces with different sizes, a sufficiently large working range and a working path can be set for the translation device in advance; a more accurate approach is to perform edge detection on the workpiece by the image processing module to obtain the size of the workpiece and thereby generate the working range and working path of the translation device. However, the rough machining process in step B is not a core point of the present invention, and is not described herein.
It should be noted that, in the above method, the image information processing process can be implemented by using various software in the prior art, and this embodiment provides one of the implementation manners:
the step C of converting the acquired image into a gray image can be realized by means of an rgb2gray function in MATLAB;
d, the statistical method of the pixel points in the step E can be realized by means of a size function in MATLAB, wherein the statistical method of the number of the flaw points can be realized by filtering flaw pixel points;
the picking up of the coordinates of the defect points in step G can be done by means of the ginput function in MATLAB.
The above description of the implementation is used to facilitate understanding, and does not represent that only one function described above is required to implement the corresponding function; nor does it represent that only this one method can implement the corresponding function in MATLAB; and not to represent that the corresponding functionality can only be implemented in MATLAB.
In summary, the above description of the image information processing process does not limit the present invention, and there are several implementation methods in the prior art, which are not described herein again.
In addition, to complete the control of the translation device by the control unit in step G, a position sensor may be further disposed on the translation device to acquire the position coordinates of the translation device. The position sensor comprises a reference end and a follow-up end arranged on the translation device, the reference end and the follow-up end work cooperatively to generate coordinates of the translation device, and the control unit controls the translation device to move according to the coordinate information. Obviously, many other ways of providing a light sensor etc. may be possible to obtain the coordinates of the translation means.
The gray value alpha is the gray value of each pixel point after the acquired image is converted into a gray image, and the value range of the gray value alpha is 0-255, wherein 255 represents white and 0 represents black.
Preferably, the image processing module converts the acquired image into a gray image by using Gamma correction, wherein the gray value α satisfies:
Figure BDA0003048874050000081
wherein R, G, B represents the color value of the corresponding color of each pixel point in the collected image. It is only for the purpose of showing the relationship between the gray values α and R, G, B to further clarify the meaning of α, and does not mean that the image processing module needs to use the algorithm in the process of converting the image by software.
For example, in an iron workpiece, the iron is brighter, and the gray value is closer to 255. And the flaws on the iron workpiece are usually oxide scales or iron rust, the color of the oxide scales is gray black, the color of the iron rust is reddish brown, and the gray value of the two flaw colors is closer to 0. Therefore, an appropriate gradation threshold value T can be set empirically in the present embodiment. Such as: the gray value of light color corresponding to the metal color is T1The gray value of the dark color corresponding to the flaw is T2Then, the set gray threshold T should satisfy:
T2< grayscale threshold T < T1
When the gray value alpha of a pixel point is less than T, the color of the pixel point is darker, and the pixel point is judged to be a flaw point; when the gray value alpha of a pixel point is larger than or equal to T, the color of the pixel point is lighter, and the pixel point is judged to be a qualified point after being processed.
Therefore, the purpose of step E is to distinguish the qualified points from the defective points by means of image recognition, and count the number of defective points.
Theta in step FmAnd the requirement of the treatment degree of the flaw points on the surface of the workpiece in the actual machining process is expressed. Preferably, θm0.01, i.e. when the defect points are occupied after processingWhen the area is not more than 1% of the surface area of the workpiece, the processing result of the time is satisfactory and acceptable.
The step E is set empirically when setting the gray level threshold T, and needs to be adjusted according to different workpieces. It is easy to think that it is helpful to the processing effect if a more standard gray level threshold T can be obtained for a certain workpiece by adding several steps.
Thus, the method further comprises step a: the camera device shoots a standard workpiece to generate a standard pattern, and the image processing module converts the standard pattern into a standard gray image and generates a gray histogram. FIG. 2 shows a gray histogram generated from a standard gray image, in which point H is the peak point of the image, and the gray value corresponding to point H is αhAnd E, setting the gray threshold T in the step E to meet the following conditions:
T＝αh-20
the meaning of step A is further explained below: in an ideal situation (i.e., the surface of the workpiece is considered to be completely cleaned, and the deviation of the image pickup angle to the color of each point of the image is not considered), when a standard gray-scale histogram is generated for a standard workpiece, only one gray-scale value (the image is a straight line perpendicular to the horizontal axis) appears on the histogram. However, due to the above-mentioned interference factors, even the machined workpiece may have sporadic defect points; and the captured image is subjected to the change of the light angle, and even if the captured image is the qualified point, the color of the captured image is recognized by a machine to be deviated, so that a gray histogram as shown in fig. 2 is actually generated.
The H point in FIG. 2 represents the gray value of the qualified point on the surface of the workpiece and the number of times the gray value appears, and the corresponding gray value is αh(ii) a L points are the gray value of the residual flaw point and the occurrence frequency of the gray value, and the corresponding gray value is alphal. Under the influence of the illumination angle and the shooting angle, the color of the qualified point is slightly lightened or weakened when being recognized. Thus, in practice, at [ alpha ]h-β，αh+β]Points within the range are qualified points, and the value of β does not generally exceed 20, so the grayscale threshold T is set to (α)h-20) the interference caused by the deviation can be effectively avoided.
Further, another way may be to set the gradation threshold value T to satisfy:
Figure BDA0003048874050000101
however, when a plurality of approximate L points appear in the gray histogram, the approximate L points need to be filtered to obtain L points adjacent to the H point and calculated. This method is more complicated than the above steps, but the technical effect is not improved much, and only the above simple introduction is made here.
The invention also discloses a shot blasting machine for realizing the workpiece surface processing method based on image recognition, and please refer to fig. 3, fig. 4 and fig. 5, wherein fig. 3 is a schematic structural diagram of the shot blasting machine; FIG. 4 is a schematic diagram of the internal structure of the shot blasting machine; fig. 5 is a schematic structural diagram of the housing of the blasting chamber 1 in fig. 4, in order to more clearly show the internal structure of the blasting machine. Among these, the image processing module 5 and the control unit 6 are electronic control elements, not explicitly shown in the figure. The shot blasting machine is further explained with reference to the attached drawings as follows:
a shot blasting machine comprising: a shot blasting chamber 1; the shot blasting device 2 comprises a shot blasting device 21 and a shot conveying pipeline 22; the shot blasting machine comprises a translation device 3, the translation device 3 is arranged in the shot blasting chamber 1 to move on a certain horizontal plane in a translation mode, the shot blasting machine 21 is arranged on the translation device 3, a nozzle of the shot blasting machine 21 faces a workpiece, and the translation device 3 drives the shot blasting machine 21 to move on the same horizontal plane; the camera device 4 is arranged at the top of the shot blasting chamber 1, the camera device 4 is used for shooting a workpiece and transmitting a shot image to the image processing module 5, and the camera device 4 can be an industrial camera; the image processing module 5 converts the captured image into a gray image through a software algorithm, identifies defective points according to gray values of pixel points on the gray image, and generates identification information, where the identification information includes: the number of defective pixel points, the total number of gray image pixel points and the coordinates of the defective pixel points.
The control unit 6 obtains the identification information, the control unit 6 generates a control signal according to the identification information, and the control unit 6 is electrically connected with the shot blasting device 2, the translation device 3, the camera device 4 and the image processing module 5 respectively so as to control the shot blasting device 2, the translation device 3, the camera device 4 and the image processing module 5 to work cooperatively.
The control unit 6 of the shot blasting machine judges whether the workpiece is qualified or not by judging the proportion of the defective pixel points to the total number of the gray image pixel points, determines the positions of the defective points by picking up the coordinates of the defective pixel points under the condition of unqualified workpiece, and controls the translation device 3 to drive the shot blasting machine 21 to perform secondary processing on the defective points. The working time of the shot blasting machine is not a value preset according to experience any more, the repeated operation steps caused by improper processing can be effectively avoided, the processing effect is good, and the efficiency is high.
Further, the present embodiment provides a structure of the translation device 3 to meet the above functional requirements. The translation device 3 comprises a slide bar 31 and a slide block 32, the slide bar 31 is arranged on the opposite side wall surface of the shot blasting chamber 1 so as to be along y1-y2Sliding along the direction, the sliding block 32 is sleeved on the sliding rod 31 to slide along the x direction1-x2Directional sliding, a position sensor is provided on the slider 32 to generate the position coordinates (x, y) of the slider. The translation device 3 is electrically connected with the control unit 6, the sliding rod 31 and the sliding block 32 on the translation device 3 are driven by a motor, and the control unit 6 controls in a driving link. As described above, the image processing module 5 can identify the defect and pick up the coordinates of the defect, and at this time, the slider 32 can be accurately controlled to drive the impeller head 21 to slide above the defect by only associating the coordinates of the defect with the coordinates of the slider 32, which can be realized in the prior art.
It should be noted that the position sensor on the sliding block 32 includes a plurality of reference ends fixedly arranged and a follower end mounted on the sliding block 32, and the coordinates of the sliding block 32 can be determined by the distance relationship between the follower end and each reference end, so that the number of the reference ends is at least 3. In addition, the position sensor can be replaced by an optical sensor, which is not described herein.
In order to obtain a better shooting effect, the camera 4 is preferably arranged at the top center of the shot blasting chamber 1. In addition, a light source device 8 can be arranged at the top of the shot blasting chamber 1 to provide better illumination adjustment, and the light source device 8 can be an LED lamp or other devices. However, the light source device 8 is not essential here, and the conventional imaging device 4 often includes a function of taking a photograph and exposing.
After the workpiece is shot-blasted, some shot blast, impurities or dust may remain on the surface of the workpiece, which may affect the image recognition effect. In order to remove the residue, the present embodiment further includes an air supply device 9, and the air supply device 9 is connected to the blasting chamber 1. As shown in fig. 4 and 6, the blower 9 includes a blower 91 and a fan 92 disposed in the blower 91, the blower 91 is provided with an air outlet, the air outlet is provided with a grill 93, and the grill 93 prevents foreign matters from entering the blower 9.
Although the above detailed description has been given with reference to specific embodiments, the scope of the present invention should not be limited by the following claims. The method claims are included for some steps, which are given a sequence order for convenience of description, but this does not mean that the steps can be executed in the sequence order given in the embodiments of the present invention. Those skilled in the art can implement the principles of the present invention, and it is within the scope of the present invention to change the order of some of the steps.

Claims (9)

1. A workpiece surface treatment method based on image recognition is applied to a shot blasting machine and is characterized in that: the shot blasting machine comprises a shot blasting device, a translation device, a camera device, an image processing module and a control unit;
the translation device drives the shot blasting devices to move on the same horizontal plane;
the camera device is used for shooting a workpiece and transmitting a shot image to the image processing module;
the image processing module is used for identifying and processing the information in the image to obtain identification information;
the control unit generates a control signal according to the identification information so as to control the shot blasting device, the translation device, the camera device and the image processing module to work cooperatively;
the method for processing the surface of the workpiece comprises the following specific steps:
and B: placing a workpiece to be processed under a shot blasting device, and starting a shot blasting machine to perform rough machining on the workpiece to be processed;
and C: starting a camera device to acquire an image of the roughly machined workpiece, and transmitting the image to the image processing module, wherein the image processing module converts the image into a gray image, and the gray value of each pixel point on the gray image is alpha;
step D: the image processing module counts the number of total pixel points in the gray level image to be N;
step E: setting a gray threshold T, when the gray value of a pixel point meets alpha < T, judging the pixel point as a defective pixel point by an image processing module, and counting the number of the defective pixel points as n by the image processing module;
step F: the control unit calculates the proportion theta of the flaw area to the workpiece area, and the theta is N/N, and sets a standard value thetamE.g. theta ≦ thetamJudging to be qualified, and finishing shot blasting work; e.g. theta > thetamIf the judgment result is unqualified, continuing to execute the step G;
step G: the image processing module picks up the coordinates of the flaw points and sends the coordinates of the flaw points to the control unit, the control unit controls the translation device to drive the shot blasting device to move to the coordinates of each flaw point, finish machining shot blasting is carried out, and after finishing, the step C is returned to and continuously executed;
the standard value thetamIs the expected value of the surface treatment effect of the workpiece.
2. The method of claim 1, wherein the method comprises the following steps: in step C, the image processing module converts the acquired image into a gray image by Gamma correction, where the gray value α satisfies:
Figure FDA0003048874040000021
r, G, B represents the color value of the corresponding color of each pixel point in the collected image.
3. The method of claim 1, wherein the method comprises the following steps: the standard value thetam＝0.01。
4. A workpiece surface processing method based on image recognition according to any one of claims 1-3, characterized by: the workpiece surface treatment method also comprises a step A before the step B,
step A: the camera device shoots a standard workpiece to generate a standard pattern, the image processing module converts the standard pattern into a standard gray image and generates a gray histogram, and the gray value corresponding to the peak value in the gray histogram is alphahAnd E, setting the gray threshold T in the step E to meet the following conditions:
T＝αh-20。
5. a shot blasting machine, to which the image recognition-based workpiece surface treatment method according to any one of claims 1 to 4 is applied, characterized by comprising:
a shot blasting chamber;
the shot blasting device comprises a shot blasting device and a shot conveying pipeline;
the translation device is arranged in the shot blasting chamber, the shot blasting device is arranged in the translation device, and the translation device is used for driving the shot blasting devices to move on the same horizontal plane;
the camera device is arranged at the top of the shot blasting chamber and used for shooting a workpiece and transmitting a shot image to the image processing module;
the image processing module is configured to convert the captured image into a grayscale image, identify a defective point according to a grayscale value of a pixel point on the grayscale image, and generate identification information, where the identification information includes: the number of defective pixel points, the total number of the gray image pixel points and the coordinates of the defective pixel points;
and the control unit generates a control signal according to the identification information so as to control the shot blasting device, the translation device, the camera device and the image processing module to work cooperatively.
6. The shot blasting machine of claim 5, wherein:
the translation device comprises a sliding rod and a sliding block, and the sliding rod is arranged on the opposite side wall surface of the shot blasting chamber to slide horizontally;
the sliding block is sleeved on the sliding rod to slide along the sliding rod, and the impeller head is arranged on the sliding block and slides synchronously with the sliding block;
the translation device is electrically connected with the control unit, a position sensor is arranged on the sliding block to send the position information of the sliding block to the control unit, and the control unit controls the translation device to drive the shot blasting device to slide to a flaw point position and perform shot blasting.
7. The shot blasting machine of claim 5, wherein: the camera device is installed in the center of the top of the shot blasting chamber.
8. The shot blasting machine of claim 5, wherein: the shot blasting machine further comprises a light source device, and the light source device is installed at the top of the shot blasting chamber.
9. Shot-blasting machine according to any one of claims 5 to 8, characterized in that: the shot blasting machine further comprises an air supply device, the air supply device comprises an air box and a fan arranged in the air box, the air box is provided with an air outlet, and a grid is arranged on the air outlet.
CN202110480127.8A 2021-04-30 2021-04-30 Workpiece surface treatment method based on image recognition and shot blasting machine Pending CN113134791A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110480127.8A CN113134791A (en) 2021-04-30 2021-04-30 Workpiece surface treatment method based on image recognition and shot blasting machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110480127.8A CN113134791A (en) 2021-04-30 2021-04-30 Workpiece surface treatment method based on image recognition and shot blasting machine

Publications (1)

Publication Number Publication Date
CN113134791A true CN113134791A (en) 2021-07-20

Family

ID=76816782

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110480127.8A Pending CN113134791A (en) 2021-04-30 2021-04-30 Workpiece surface treatment method based on image recognition and shot blasting machine

Country Status (1)

Country Link
CN (1) CN113134791A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114754706A (en) * 2022-04-11 2022-07-15 广东机电职业技术学院 Mechanical part machining surface roughness online detection method and system
CN115351713A (en) * 2022-10-19 2022-11-18 武汉艾极涂科技有限公司 Sand blasting method, device, equipment and storage medium based on image recognition

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0569317A (en) * 1991-09-17 1993-03-23 Nippon Steel Corp Method for grinding flaw of steel piece
CN105729267A (en) * 2016-02-03 2016-07-06 华中科技大学 Edging device and method based on visual control
CN106530291A (en) * 2016-10-28 2017-03-22 重庆工商职业学院 Polished surface detection method and system based on image processing
CN106918602A (en) * 2017-04-13 2017-07-04 北京海风智能科技有限责任公司 A kind of detection method of surface flaw based on machine vision of robust
CN111421425A (en) * 2020-03-11 2020-07-17 东北大学 Metal surface grinding system based on industrial vision
CN112241699A (en) * 2020-10-13 2021-01-19 无锡先导智能装备股份有限公司 Object defect category identification method and device, computer equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0569317A (en) * 1991-09-17 1993-03-23 Nippon Steel Corp Method for grinding flaw of steel piece
CN105729267A (en) * 2016-02-03 2016-07-06 华中科技大学 Edging device and method based on visual control
CN106530291A (en) * 2016-10-28 2017-03-22 重庆工商职业学院 Polished surface detection method and system based on image processing
CN106918602A (en) * 2017-04-13 2017-07-04 北京海风智能科技有限责任公司 A kind of detection method of surface flaw based on machine vision of robust
CN111421425A (en) * 2020-03-11 2020-07-17 东北大学 Metal surface grinding system based on industrial vision
CN112241699A (en) * 2020-10-13 2021-01-19 无锡先导智能装备股份有限公司 Object defect category identification method and device, computer equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114754706A (en) * 2022-04-11 2022-07-15 广东机电职业技术学院 Mechanical part machining surface roughness online detection method and system
CN115351713A (en) * 2022-10-19 2022-11-18 武汉艾极涂科技有限公司 Sand blasting method, device, equipment and storage medium based on image recognition
CN115351713B (en) * 2022-10-19 2023-06-02 武汉艾极涂科技有限公司 Sand blasting method, device, equipment and storage medium based on image recognition

Similar Documents

Publication Publication Date Title
CN113134791A (en) Workpiece surface treatment method based on image recognition and shot blasting machine
CN108226164B (en) Robot polishing method and system based on visual detection
CN110163853B (en) Edge defect detection method
CN108230324B (en) Visual detection method for microdefect on surface of magnetic shoe
CN111539582B (en) Image processing-based steel plate cutting planning device and method
CN112084964A (en) Product identification apparatus, method and storage medium
CN112734720B (en) Ship hull laser cleaning in-situ detection method and system based on visual identification
US6490369B1 (en) Method of viewing and identifying a part for a robot manipulator
CN109358067A (en) Motor ring varistor defect detecting system based on computer vision and method
CN109949362A (en) A kind of material visible detection method
CN111968100B (en) Machine vision detection method and system
CN110582159A (en) FPC bonding pad surface defect processing system and method
CN113878576B (en) Robot vision sorting process programming method
CN113822810A (en) Method for positioning workpiece in three-dimensional space based on machine vision
CN111833350B (en) Machine vision detection method and system
CN110728286A (en) Abrasive belt grinding material removal rate identification method based on spark image
CN114820475A (en) Edge identification method and system, wafer processing device and method for determining concentric state of wafer and processing table
CN116922270B (en) Intelligent control system and method for sand blasting machine
US11935216B2 (en) Vision inspection system and method of inspecting parts
CN110013986B (en) Jet flow rust removing equipment
CN116681664A (en) Detection method and device for operation of stamping equipment
US11378520B2 (en) Auto focus function for vision inspection system
CN115830018B (en) Carbon block detection method and system based on deep learning and binocular vision
CN114345841B (en) Control method in laser cleaning process and laser cleaning control system
CN112184670B (en) Detection method for shot peening strengthening surface coverage rate

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