Dispensing machine three-dimensional path planning method

Through the three-dimensional path planning method, the motion path of the dispenser is automatically calculated using image data and path planning models, solving the problem of manually setting the dispensing path in the existing technology, and improving production efficiency and dispensing accuracy.

CN119472495APending Publication Date: 2025-02-18KUNSHAN WENHUI ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411533839.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-31
Publication Date
2025-02-18

AI Technical Summary

Technical Problem

In the prior art, the path setting of the dispenser requires manual adjustment, which leads to cumbersome operation and error-prone, affecting production efficiency and product quality.

Method used

The three-dimensional path planning method is adopted to automatically calculate the dispensing path through the image data and path planning model of the workpiece, and the three-dimensional coordinates and dimension information of the dispensing mark are used to generate the motion path of the dispensing machine.

Benefits of technology

Automatic dispensing path setting is realized, avoiding manual adjustment errors, and improving the efficiency of equipment and dispensing accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119472495A_ABST
    Figure CN119472495A_ABST
Patent Text Reader

Abstract

The invention discloses a three-dimensional path planning method for a dispensing machine. The method comprises the following steps: performing dispensing marking on a workpiece; acquiring image data of the workpiece, and acquiring three-dimensional coordinates of the dispensing mark according to the image data; and a motion path of the dispenser is obtained through the path planning model, and the three-dimensional coordinates of the dispensing marks are sequentially connected through the motion path. According to the three-dimensional path planning method for the dispensing machine, the dispensing path is automatically calculated through the image data of the workpiece and the path planning model, the problems that errors are prone to occurring and operation is tedious due to manual setting are solved, and the use efficiency of equipment is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of mechanical processing, and in particular relates to a three-dimensional path planning method for a glue dispensing machine. Background Art

[0002] Glue dispensing machines are mainly used for precise dispensing and fluid control of adhesives, lubricants, sealants and coatings to meet the needs of product fixing, sealing, bonding, welding, filling, coating, spraying, potting, marking and other process applications. Glue dispensing machines can replace manual dispensing and are widely used in industrial production, such as integrated circuits, printed circuit boards, electronic components, automotive parts, etc., significantly improving production efficiency and product quality.

[0003] In the prior art, the specific dispensing path is set manually. The person manually observes the position of the dispensing head and moves and adjusts the position of the dispensing head to a suitable dispensing position. The manual setting and adjustment is troublesome, the operation is cumbersome, and it is easy to make mistakes. Summary of the invention

[0004] The purpose of the present invention is to provide a three-dimensional path planning method for a dispensing machine, so as to solve the problems in the prior art of troublesome manual setting and adjustment, cumbersome operation and easy error.

[0005] To this end, the present invention provides a three-dimensional path planning method for a glue dispensing machine, comprising the following steps: performing glue dispensing marking on a workpiece;

[0006] Acquire image data of the workpiece, and obtain the three-dimensional coordinates of the dispensing mark according to the image data;

[0007] The motion path of the glue dispensing machine is obtained through the path planning model, and the motion path connects the three-dimensional coordinates of the glue dispensing marks in sequence.

[0008] Preferably, size information is provided on the glue dispensing mark.

[0009] Preferably, the step of acquiring image data of the workpiece and obtaining the three-dimensional coordinates of the glue spot mark according to the image data comprises:

[0010] The image of the workpiece is captured by a camera to obtain image data of the workpiece;

[0011] Identify the pixel coordinates of the dispensing mark in the image through an image recognition algorithm;

[0012] The three-dimensional coordinates of the dispensing mark in the dispensing machine coordinate system are obtained based on the hand-eye calibration.

[0013] Preferably, the image data of the workpiece is RGB color image data or depth image data.

[0014] Preferably, the image recognition algorithm is an edge detection algorithm or a deep learning algorithm.

[0015] Preferably, the size information of the glue spot mark is read according to the pixel coordinates of the glue spot mark in the image.

[0016] Preferably, the glue output of the glue dispensing machine at the glue dispensing mark is obtained according to the size information of the glue dispensing mark.

[0017] Preferably, the steps of obtaining the motion path of the dispensing machine through the path planning model include: initializing the dispensing mark; looping each dispensing mark and calculating the total cost until all dispensing marks are calculated; and backtracking from the last dispensing mark to the starting position to obtain a complete dispensing path.

[0018] Preferably, the step of initializing the glue dispensing mark includes:

[0019] The data structure is created by taking the initial position of the dispensing machine as the starting position and the dispensing mark as the dispensing position set;

[0020] Set the actual cost of the starting position to 0, and calculate the estimated cost from the starting position to each dispensing position;

[0021] Calculate the total cost of the starting position.

[0022] Preferably, the step of looping each glue dispensing mark and calculating the total cost until all glue dispensing marks are calculated includes:

[0023] Calculate the actual cost for each dispensing mark;

[0024] Calculate the estimated cost of the glue mark adjacent to it;

[0025] Calculate the total cost of the glue mark adjacent to it.

[0026] Beneficial effects:

[0027] 1. The present invention provides a three-dimensional path planning method for a dispensing machine, which automatically calculates the dispensing path through the image data of the workpiece and the path planning model, avoids the problems of easy errors in manual setting and cumbersome operation, and improves the efficiency of equipment use.

[0028] 2. In the present invention, the size information contained in the dispensing mark enables the dispensing machine to obtain the amount of glue at the position of the dispensing mark without manual setting, thereby improving the dispensing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 The present invention is a flowchart of a three-dimensional path planning method for a dispensing machine.

[0031] Figure 2 This is a flow chart of step S2 of a three-dimensional path planning method for a dispensing machine in the present invention.

[0032] Figure 3 This is a flow chart of step S3 of a three-dimensional path planning method for a glue dispensing machine in the present invention. DETAILED DESCRIPTION

[0033] The content of the present invention can be more easily understood by selecting the following detailed description of the preferred implementation method of the present invention and the embodiments included. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art to which the present invention belongs. When there is a conflict, the definition in this specification shall prevail.

[0034] Embodiment 1:

[0035] like Figure 1 As shown, this embodiment provides a three-dimensional path planning method for a dispensing machine, including the following steps:

[0036] S1. Glue marking on the workpiece;

[0037] The glue dispensing mark is provided with size information. The glue dispensing mark is a cross, a circle, or a square. In one embodiment, the glue dispensing mark is a cross, and the size information is the length of the horizontal or vertical line of the cross. In another embodiment, the glue dispensing mark is the center of a circle, and the size information is the diameter of the circle. In another embodiment, the glue dispensing mark is a square, and the size information is the side length of the square. The size information is used to represent the amount of glue discharged at the glue dispensing mark. The larger the size, the more glue is discharged, and the smaller the size, the smaller the glue is discharged. The color of the glue dispensing mark has a large contrast with the color of the workpiece, such as if the workpiece is silver-white and the glue dispensing mark is black, or if the workpiece is black and the glue dispensing mark is white.

[0038] S2, acquiring image data of the workpiece, and obtaining the three-dimensional coordinates of the dispensing mark according to the image data;

[0039] Among them, Figure 2 As shown, the steps of S2 include:

[0040] S21. Capture an image of a workpiece through a camera to obtain image data of the workpiece; the image data of the workpiece is RGB color image data or depth image data.

[0041] S22, identifying the pixel coordinates of the glue dispensing mark in the image by an image recognition algorithm; the image recognition algorithm is an edge detection algorithm or a deep learning algorithm. Reading the size information of the glue dispensing mark according to the pixel coordinates of the glue dispensing mark in the image. Obtaining the glue output of the glue dispensing machine at the glue dispensing mark according to the size information of the glue dispensing mark.

[0042] Among them, the edge detection algorithm can be selected from Roberts Cross operator, Prewitt operator, Sobel operator, Kirsch operator, Laplacian operator and Canny operator, and the deep learning algorithm can be selected from CNN algorithm, SSD algorithm, YOLO algorithm and FCN algorithm. The edge detection algorithm or deep learning algorithm can identify the edge of the glue mark by the contrast between the glue mark and the workpiece color, so as to obtain the pixel coordinates of the glue mark at the end point of the image.

[0043] According to the pixel coordinates of the glue dispensing mark, the pixel coordinate range of the glue dispensing mark in the image can be obtained, thereby obtaining the size information. The glue output of the glue dispensing machine at the glue dispensing mark is B=KL, where B is the glue output at the glue dispensing mark, L is the size information, and K is the proportional coefficient. The size information can be used to identify the glue output of the glue dispensing machine at the glue dispensing mark according to the image.

[0044] S23. Obtain the three-dimensional coordinates of the dispensing mark in the dispensing machine coordinate system according to the hand-eye calibration.

[0045] Hand-eye calibration is used to obtain the conversion relationship between the dispensing machine coordinate system and the camera's pixel coordinate system. After obtaining the pixel coordinates of the dispensing mark, the three-dimensional coordinates of the dispensing mark in the dispensing machine coordinate system can be obtained based on the hand-eye calibration.

[0046] S3. The motion path of the glue dispensing machine is obtained through the path planning model, and the motion path connects the three-dimensional coordinates of the glue dispensing marks in sequence.

[0047] Among them, Figure 3 As shown, the steps of S3 include:

[0048] S31, initializing the dispensing mark;

[0049] Take the initial position of the dispensing machine as the starting position P 0 =(x 0 ,y 0 ,z 0 ), the glue point mark is used as the glue point position set P i =(x i ,yi ,z i ), create data structure;

[0050] The data structure includes open list, closed list, path list and dispensing order list. The development list is used to store the dispensing positions to be explored. Each dispensing position contains the coordinates of the current position, the actual cost g from the starting position to the current position, the estimated cost h from the current position to the target point, the total cost f = g + h and the parent pointer. The closed list is used to store the nodes that have been explored. The path list is used to store the final dispensing path, and the dispensing order list is used to record the order of dispensing.

[0051] Set the actual cost g(P 0 )=0, calculate the estimated cost from the starting position to each dispensing position, that is,

[0052] Calculate the total cost f(P 0 )=g(P 0 )+h(P 0 ,P i ).

[0053] S32, looping each glue dispensing mark and calculating the total cost until all glue dispensing marks are calculated;

[0054] Select the glue mark with the minimum total cost from the open list as the current position. If the current glue mark is a glue position that has not been visited, mark it as visited and add it to the path list and glue order list. If all glue marks have been visited, the algorithm ends, otherwise continue to perform the following steps:

[0055] For each adjacent glue mark of the current glue mark: If the adjacent glue mark is an unvisited glue mark or the starting position and is not in the closed list, calculate its actual cost g ′ .

[0056] Calculate the estimated cost h of adjacent glue marks ′ If the adjacent dispensing mark is an unvisited dispensing location, then h ′ is the estimated cost from the adjacent glue mark to the next unvisited glue mark; if the adjacent glue mark is the starting position, then h ′ is the estimated cost from the adjacent dispensing mark to the starting position.

[0057] Calculate the total cost f of adjacent glue marks ′ =g ′ +h ′ .

[0058] If the adjacent dispensing mark is not in the open list, it is added to the open list and its parent dispensing mark is set as the current dispensing mark.

[0059] If the adjacent glue mark is already in the open list, and the new total cost f ′ If it is less than the original total cost, its actual cost, estimated cost and total cost are updated, and its parent dispensing mark is set as the current dispensing mark.

[0060] S33, backtracking from the last dispensing mark to the path of the starting position to obtain a complete dispensing path.

[0061] When all the glue markers have been visited and the algorithm ends, starting from the last glue marker, by backtracking the parent glue marker of each node, a path from the last glue marker to the starting position is constructed, and it is reversed to obtain the complete glue path.

[0062] The order of dispensing is stored in the dispensing order list.

[0063] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A three-dimensional path planning method for a dispensing machine, characterized in that: The steps include: Make glue marks on the workpiece; Acquire image data of the workpiece, and obtain the three-dimensional coordinates of the dispensing mark according to the image data; The motion path of the glue dispensing machine is obtained through the path planning model, and the motion path connects the three-dimensional coordinates of the glue dispensing marks in sequence.

2. A three-dimensional path planning method for a dispensing machine according to claim 1, characterized in that: The glue dispensing mark is provided with size information.

3. A three-dimensional path planning method for a dispensing machine according to claim 2, characterized in that: The step of acquiring image data of the workpiece and obtaining the three-dimensional coordinates of the glue dispensing mark according to the image data comprises: The image of the workpiece is captured by a camera to obtain image data of the workpiece; Identify the pixel coordinates of the dispensing mark in the image through an image recognition algorithm; The three-dimensional coordinates of the dispensing mark in the dispensing machine coordinate system are obtained based on the hand-eye calibration.

4. A three-dimensional path planning method for a dispensing machine according to claim 3, characterized in that: The image data of the workpiece is RGB color image data or depth image data.

5. A three-dimensional path planning method for a dispensing machine according to claim 3, characterized in that: The image recognition algorithm is an edge detection algorithm or a deep learning algorithm.

6. A three-dimensional path planning method for a dispensing machine according to claim 5, characterized in that: The size information of the glue spot mark is read according to the pixel coordinates of the glue spot mark in the image.

7. A three-dimensional path planning method for a dispensing machine according to claim 6, characterized in that: The glue output of the glue dispensing machine at the glue dispensing mark is obtained according to the size information of the glue dispensing mark.

8. A three-dimensional path planning method for a dispensing machine according to claim 1, characterized in that: The steps of obtaining the motion path of the dispensing machine through the path planning model include: initializing the dispensing mark; looping each dispensing mark and calculating the total cost until all the dispensing marks are calculated; and backtracking from the last dispensing mark to the starting position to obtain a complete dispensing path.

9. A three-dimensional path planning method for a dispensing machine according to claim 8, characterized in that: The step of initializing the dispensing mark comprises: The data structure is created by taking the initial position of the dispensing machine as the starting position and the dispensing mark as the dispensing position set; Set the actual cost of the starting position to 0, and calculate the estimated cost from the starting position to each dispensing position; Calculate the total cost of the starting position.

10. A three-dimensional path planning method for a dispensing machine according to claim 8, characterized in that: The step of looping each dispensing mark and calculating the total cost until all dispensing marks are calculated includes: Calculate the actual cost for each dispensing mark; Calculate the estimated cost of the glue mark adjacent to it; Calculate the total cost of the glue mark adjacent to it.