Robotic scraping method and system applied to machine tool worktables

Abstract

This invention belongs to the field of automated machine tool processing, and is a robotic scraping method and system applied to machine tool worktables. The method includes: acquiring a workpiece image and calibrating the acquired image; identifying the work area in the workpiece image and extracting contour information to obtain a region of interest (ROI); generating a scraping contour with given parameters and a uniformly distributed dot matrix within the ROI; traversing the points in the generated dot matrix and determining whether each point is within the scraping contour (points within the contour are considered heavy scraping points, and points outside the contour are considered light scraping points), thus obtaining heavy and light scraping point information; and sending this information to the robot via instructions, allowing the robot to perform scraping operations based on the scraping point information. This invention allows for the selection of appropriate scraping contours according to actual needs, and scrapes the worktable surface based on these contours, achieving a high degree of automation and effectively solving the problem of product quality degradation caused by a smooth machine tool worktable.

Description

Technical Field

[0001] This invention belongs to the field of automated machine tool processing, specifically a robotic scraping method and system applied to the worktable of a machine tool. Background Technology

[0002] Scraping is a crucial process in machine tool manufacturing, ensuring machine tool precision and determining its mechanical performance. Currently, scraping is entirely manual across the industry, resulting in low efficiency, high labor intensity, and a heavy reliance on the experience of the workers, which can have long-term negative impacts on their physical and mental health. However, with the development of industrial automation and artificial intelligence technologies, machines are poised to replace manual scraping in industrial applications.

[0003] Currently, machine tool worktables are flattened using grinding processes. However, this also results in a relatively smooth surface with a low coefficient of friction. This leads to vibrations during workpiece and fixture clamping and machining, and the excessive smoothness of the worktable surface also makes it prone to displacement. Excessive clamping force can cause deformation of the workpiece and fixture, compromising product quality. Furthermore, wear on the worktable surface is difficult to detect; if wear is not promptly identified, it directly impacts product quality. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a robotic scraping method and system for machine tool worktables. This system allows for the selection of appropriate scraping contours based on actual production requirements. After grinding, the worktable surface is then scraped according to the scraping contours. This method reduces manual labor intensity and increases automation. The scraped worktable surface effectively solves the problem of reduced product quality caused by a smooth machine tool worktable.

[0005] The method of the present invention is achieved through the following technical solution: a robotic scraping method applied to a machine tool worktable, comprising the following steps:

[0006] Acquire workpiece images and calibrate the acquired workpiece images;

[0007] Work area recognition is performed on the workpiece image to extract contour information and obtain the region of interest (ROI).

[0008] Within the region of interest (ROI), generate a shovel profile and a uniformly distributed dot matrix with given parameters;

[0009] Traverse the points in the generated dot matrix, determine whether each point in the dot matrix is ​​within the shovel outline, points within the shovel outline are heavy shovel points, and points outside the shovel outline are light shovel points, and obtain the light and heavy shovel point information.

[0010] The robot receives instructions to perform scraping and shoveling operations based on the information regarding the light and heavy shoveling points.

[0011] The system of the present invention is achieved through the following technical solution: a robotic scraping system applied to a machine tool worktable, comprising:

[0012] The image acquisition module is used to acquire workpiece images and calibrate the acquired workpiece images;

[0013] The region recognition module is used to identify the working area of ​​the workpiece image, extract the contour information in the workpiece image, and obtain the region of interest (ROI).

[0014] The contour and dot matrix generation module generates a shovel contour and a uniformly distributed dot matrix with given parameters within the region of interest (ROI).

[0015] The light and heavy shovel point discrimination module traverses the points in the generated dot matrix and determines whether each point in the dot matrix is ​​within the shovel outline. Points within the shovel outline are heavy shovel points, and points outside the shovel outline are light shovel points, thus obtaining light and heavy shovel point information.

[0016] The scraping module sends information about the light and heavy scraping points to the robot via instructions, and the robot performs scraping and shaving operations based on this information.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] 1. The present invention can select the corresponding scraping contour according to the scraping requirements in the actual production process, and then scrape the surface of the worktable after grinding according to the scraping contour; the scraped worktable surface can increase the contact rigidity between the machined part and the worktable surface, effectively solve the problem that the workpiece is easy to shift due to the smoothness of the table surface, and improve the quality of the parts processing, such as improving the surface finish of the machined parts and effectively reducing the deformation of the parts caused by excessive clamping.

[0019] 2. The work surface after scraping is easy to observe and detect whether wear has occurred; therefore, the wear of the work surface can be detected in time, ensuring that the product quality is not affected by the wear of the work surface.

[0020] 3. This invention uses a robot-scraped surface to replace the traditional machined grinding surface, which can significantly reduce the labor intensity of workers, replace heavy manual labor, effectively reduce the labor intensity of workers, and achieve automation. Attached Figure Description

[0021] Figure 1 This is a flowchart of a robotic scraping method applied to a machine tool worktable in an embodiment of the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments, but the implementation of the present invention is not limited thereto.

[0023] Example

[0024] This embodiment provides a robotic scraping method applied to machine tool worktables, including the following steps:

[0025] Step S1: Use an industrial camera to acquire images of the workpiece and calibrate the acquired workpiece images.

[0026] The workpiece images acquired by the industrial camera have high imaging quality and resolution that meets the inspection requirements. Camera calibration can accurately convert the actual coordinate values ​​and pixel coordinate values ​​of the workpiece. Thus, in subsequent steps, based on the scraping points obtained from the image, the robot can accurately scrape the workpiece.

[0027] Step S2: Use the edge detection algorithm to identify the working area of ​​the workpiece image, extract the contour information in the workpiece image, and obtain the region of interest (ROI).

[0028] The identification of the working area is achieved through an edge detection algorithm, which extracts contour information from the image to obtain the Region of Interest (ROI). In this embodiment, the edge detection algorithm identifies the working area by calculating the gradient value of the workpiece image; the formula for calculating the gradient value of the workpiece image is as follows:

[0029] g x (i,j)=f(i+1,j+1)-f(i-1,j-1)+f(i-1,j+1)-f(i+1,j-1)+f(i,j+1)-f(i,j-1);

[0030] g y (i,j)=f(i+1,j+1)-f(i-1,j-1)-f(i-1,j+1)+f(i+1,j-1)+f(i,j+1)-f(i,j-1);

[0031]

[0032] θ = arctan(g) y (i,j) / g x (i,j));

[0033] In the formula g x (i,j) represents the gradient in the X direction of the workpiece image, g y(i,j) represents the gradient in the Y direction of the workpiece image, where i is the X coordinate of the workpiece image, j is the Y coordinate of the workpiece image, f(i,j) is the grayscale value of the workpiece image, g(i,j) is the gradient value of the workpiece image, and θ is the gradient direction of the workpiece image. The information of a point is saved when the gradient value g(i,j) of the workpiece image is greater than a set threshold.

[0034] Step S3: In the ROI obtained in step S2, generate the shovel profile and uniformly distributed dot matrix with given parameters.

[0035] In this embodiment, to meet various needs in industrial production, the shovel outline includes shapes such as circles, rectangles, and rhombuses. The shovel outline calculates outline points based on the selected shape and step size, and then sequentially generates a dot matrix within the outline with equal spacing in the X and Y directions.

[0036] Step S4: Traverse the points in the dot matrix generated in step S3, determine whether each point in the dot matrix is ​​within the shovel outline, take the points within the shovel outline as heavy shovel points, and take the points outside the shovel outline as light shovel points, and obtain the light and heavy shovel point information.

[0037] More specifically, within the outline of the carving pattern, the darker and larger points are the heavy carving points, while outside the outline, the lighter and smaller points are the light carving points. Heavy carving points involve deeper and larger scraping marks, requiring more cuts; light carving points involve shallower and smaller scraping marks, requiring fewer cuts.

[0038] In this embodiment, it is determined whether the points in the dot matrix in step S3 are within the shovel outline. This is done by traversing each point in the dot matrix and sequentially determining the relationship between each point and the shovel outline. The algorithm is as follows:

[0039]

[0040] In the formula, φ is the sum of the angles between the test point and all points of the shovel outline, n is the number of points in the outline, pi is the i-th point in the outline, P(i+1)%n is the (i+1)-th point in the outline, Pt is the test point, Pi.x is the X-coordinate of the i-th point in the outline, Pi.y is the Y-coordinate of the i-th point in the outline, Pt.x is the X-coordinate of the test point, and Pt.y is the Y-coordinate of the test point. If φ = 2π, it means the test point is inside the shovel outline; if φ = 0, it is outside the shovel outline.

[0041] Step S5: After the scraping point identification is completed, the light and heavy scraping point information is sent to the robot through instructions. The robot then performs scraping and shoveling operations based on the light and heavy scraping point information.

[0042] The robot performs scraping tasks based on the information of light and heavy scraping points, which can realize automated scraping, effectively reduce the intensity of manual labor, and solve the problem of easy displacement of workpieces with smooth surfaces.

[0043] In addition, robot parameters can be modified to adjust different shapes of blade patterns according to actual needs.

[0044] This embodiment also provides a robotic scraping system applied to machine tool worktables, specifically including the following modules:

[0045] The image acquisition module is used to acquire workpiece images and calibrate the acquired workpiece images;

[0046] The region recognition module is used to identify the working area of ​​the workpiece image, extract the contour information in the workpiece image, and obtain the region of interest (ROI).

[0047] The contour and dot matrix generation module generates a shovel contour and a uniformly distributed dot matrix with given parameters within the region of interest (ROI).

[0048] The light and heavy shovel point discrimination module traverses the points in the generated dot matrix and determines whether each point in the dot matrix is ​​within the shovel outline. Points within the shovel outline are heavy shovel points, and points outside the shovel outline are light shovel points, thus obtaining light and heavy shovel point information.

[0049] The scraping module sends information about the light and heavy scraping points to the robot via instructions, and the robot performs scraping and shaving operations based on this information.

[0050] The above modules are used to execute each step of the scraping method in this embodiment. For details of the execution process, please refer to steps S1-S5, which will not be repeated here.

[0051] The above description is only a preferred embodiment of the present invention, but the scope of protection of the invention patent is not limited thereto. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the scope of protection of the present invention.

Claims

1. A robotic scraping method applied to machine tool worktables, characterized in that, Includes the following steps: Acquire workpiece images and calibrate the acquired workpiece images; Work area recognition is performed on the workpiece image to extract contour information and obtain the region of interest (ROI). Within the region of interest (ROI), generate a shovel profile and a uniformly distributed dot matrix with given parameters; Traverse the points in the generated dot matrix, determine whether each point in the dot matrix is ​​within the shovel outline, points within the shovel outline are heavy shovel points, and points outside the shovel outline are light shovel points, and obtain the light and heavy shovel point information. The robot receives instructions to perform scraping and shoveling operations based on the information on the light and heavy shoveling points. Use edge detection algorithms to identify the working area in workpiece images; Edge detection algorithms identify the work area by calculating the gradient value of the workpiece image; the formula for calculating the gradient value of the workpiece image is: g x (i,j)=f(i+1,j+1)-f(i-1,j-1)+f(i-1,j+1)-f(i+1,j-1)+f(i,j+1)-f(i,j-1); g y (i,j)=f(i+1,j+1)-f(i-1,j-1)-f(i-1,j+1)+f(i+1,j-1)+f(i,j+1)-f(i,j-1); θ=arctan(g y (i,j) / g x (i,j)); In the formula g x (i,j) represents the gradient in the X direction of the workpiece image, g y (i,j) represents the gradient in the Y direction of the workpiece image, i represents the X coordinate of the workpiece image, j represents the Y coordinate of the workpiece image, f(i,j) represents the gray value of the workpiece image, g(i,j) represents the gradient value of the workpiece image, and θ represents the gradient direction of the workpiece image.

2. The robotic scraping method according to claim 1, characterized in that, To determine whether a point in the dot matrix is ​​within the shovel pattern outline, iterate through each point in the dot matrix and sequentially determine the relationship between each point and the shovel pattern outline: In the formula, φ is the sum of the angles of the lines connecting the test point to all points of the contour, n is the number of points in the contour, pi is the i-th point in the contour, P(i+1)%n is the (i+1)-th point in the contour, Pt is the test point, Pi.x is the X-coordinate of the i-th point in the contour, Pi.y is the Y-coordinate of the i-th point in the contour, Pt.x is the X-coordinate of the test point, and Pt.y is the Y-coordinate of the test point; if φ = 2π, the test point is determined to be inside the shovel contour, and if φ = 0, the test point is outside the shovel contour.

3. The robotic scraping method according to claim 1, characterized in that, The outline of the shovel is round, rectangular, or diamond-shaped.

4. A robotic scraping system applied to a machine tool worktable, characterized in that, include: The image acquisition module is used to acquire workpiece images and calibrate the acquired workpiece images; The region recognition module is used to identify the working area of ​​the workpiece image, extract the contour information in the workpiece image, and obtain the region of interest (ROI). The contour and dot matrix generation module generates a shovel contour and a uniformly distributed dot matrix with given parameters within the region of interest (ROI). The light and heavy shovel point discrimination module traverses the points in the generated dot matrix and determines whether each point in the dot matrix is ​​within the shovel outline. Points within the shovel outline are heavy shovel points, and points outside the shovel outline are light shovel points, thus obtaining light and heavy shovel point information. The scraping module sends information on light and heavy scraping points to the robot via instructions, and the robot performs scraping and shaving operations based on the information on light and heavy scraping points. The region recognition module uses an edge detection algorithm to identify the working region in the workpiece image; The edge detection algorithm identifies the working area by calculating the gradient value of the workpiece image; the formula for calculating the gradient value of the workpiece image is: g x (i,j)=f(i+1,j+1)-f(i-1,j-1)+f(i-1,j+1)-f(i+1,j-1)+f(i,j+1)-f(i,j-1); g y (i,j)=f(i+1,j+1)-f(i-1,j-1)-f(i-1,j+1)+f(i+1,j-1)+f(i,j+1)-f(i,j-1); θ=arctan(g y (i,j) / g x (i,j)); In the formula g x (i,j) represents the gradient in the X direction of the workpiece image, g y (i,j) represents the gradient in the Y direction of the workpiece image, i represents the X coordinate of the workpiece image, j represents the Y coordinate of the workpiece image, f(i,j) represents the gray value of the workpiece image, g(i,j) represents the gradient value of the workpiece image, and θ represents the gradient direction of the workpiece image.

5. The robotic scraping system according to claim 4, characterized in that, The light and heavy scraping point discrimination module determines whether a point in the dot matrix is ​​within the scraping outline. It iterates through each point in the dot matrix and sequentially judges the relationship between each point and the scraping outline: In the formula, φ is the sum of the angles of the lines connecting the test point to all points of the contour, n is the number of points in the contour, pi is the i-th point in the contour, P(i+1)%n is the (i+1)-th point in the contour, Pt is the test point, Pi.x is the X-coordinate of the i-th point in the contour, Pi.y is the Y-coordinate of the i-th point in the contour, Pt.x is the X-coordinate of the test point, and Pt.y is the Y-coordinate of the test point; if φ = 2π, the test point is determined to be inside the shovel contour, and if φ = 0, the test point is outside the shovel contour.

6. The robotic scraping system according to claim 4, characterized in that, The outline of the shovel is round, rectangular, or diamond-shaped.

Images