A laser processing method and system based on visual edge finding

Abstract

The application relates to the technical field of visual detection, and discloses a laser processing method and system based on visual edge searching, which comprises the following steps: placing a plate to be processed on a processing table of a machine tool, performing initial positioning on the edge of the plate to be processed by a monitoring camera, and obtaining an initial image by shooting; determining edge points and corner points of the plate according to the initial image, and obtaining corresponding monitoring image coordinates; converting the monitoring image coordinates of the edge points and the corner points into machine tool coordinates; controlling a cutting head and a CCD camera to move to the machine tool coordinates, performing fine positioning on the edge of the plate to be processed by the CCD camera, and obtaining the accurate edge position of the plate; and controlling the cutting head to move according to the edge position, and performing laser processing on the plate to be processed. The application can realize an adaptive edge searching process on plates with different lengths, the visual edge searching is more flexible and stable, the repeated edge searching precision is improved, the risk of collision between the cutting head and the plate is avoided, and the laser processing efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of visual inspection technology, and more specifically, to a laser processing method and system based on visual edge detection. Background Technology

[0002] Before cutting sheet metal, laser cutting equipment typically needs to determine the angle information of the sheet metal's edge and the position of its starting point (a process called edge finding). This allows the CNC machining system to accurately calculate the machine tool coordinates of the sheet metal's location, ensuring processing accuracy. Currently, the mainstream edge finding method relies on capacitive sensors, determining the edge position based on the sudden change in capacitance charge from the inside of the sheet metal to its edge. However, capacitive sensors are susceptible to instability due to various factors, especially at high edge finding speeds. When the cutting head reaches the edge, it may rapidly descend, causing collisions or even damage. This is because the sensor must remain within a constant range of the sheet metal during edge finding. If the sensor suddenly crosses the edge, it will also suddenly descend to track the sheet metal (maintaining a fixed distance), causing a collision between the cutting head and the machine tool, thus affecting the reliability and safety of the equipment during laser processing.

[0003] Furthermore, relying on sensors to find edges has poor repeatability when the starting point is different. This is because when the cutting head is moving at a high speed, the sensor will be delayed in collecting information, which means that the edge information of the board collected by the sensor is not the actual position, but a small gap. However, the gap after finding the edge is different at different starting points, so the repeatability is not high. Summary of the Invention

[0004] The purpose of this invention is to address the technical problems existing in the prior art by providing a laser processing method and system based on vision edge finding. This method can adaptively find the edges of plates of different lengths and complete the laser processing, thereby improving the accuracy of repeated edge finding and ensuring the processing efficiency of laser processing.

[0005] To address the problems mentioned above, the technical solution adopted by this invention is as follows:

[0006] This invention provides a laser processing method based on visual edge finding, the specific steps of which include the following:

[0007] The sheet material to be processed is placed on the processing table of the machine tool, and the edge of the sheet material to be processed is initially positioned by the monitoring camera to obtain the initial image;

[0008] Based on the initial image, the edge points and corner points of the board are determined, and the corresponding monitoring image coordinates are obtained;

[0009] Convert the monitoring image coordinates of the edge points and corner points into machine tool coordinates;

[0010] The cutting head and CCD camera are controlled to move to the machine tool coordinates, and the CCD camera is used to precisely position the edge of the material to be processed, so as to obtain the accurate edge position of the material.

[0011] Based on the edge position, the cutting head is controlled to move and perform laser processing on the material to be processed.

[0012] Furthermore, the step of controlling the movement of the cutting head and CCD camera according to the machine tool coordinates, and using the CCD camera to precisely locate the edge of the board material to obtain the accurate edge position of the board material, specifically includes the following steps:

[0013] Control the cutting head and CCD camera to move to the machine tool coordinates of the edge point and corner point, respectively;

[0014] The CCD camera is controlled to illuminate the edge of the board using a cross-shaped line laser light source. The cross-shaped light spots intersect with the adjacent edges of the board to capture CCD camera images.

[0015] Based on the CCD camera image, obtain the CCD camera image coordinates corresponding to the intersection of the cross-shaped light spot and the adjacent side of the plate.

[0016] The CCD camera image coordinates are converted into machine tool coordinates to obtain the precise edge position of the board material.

[0017] Furthermore, the conversion of CCD camera image coordinates to machine tool coordinates specifically includes the following steps:

[0018] The cutting head laser cuts a circle of radius R and stops at the center of the circle. The machine coordinates p1 of the cutting head are recorded.

[0019] Move the cutting head so that the CCD camera can capture a complete circle to obtain the camera calibration image, and obtain the circle center image coordinates C1, image center coordinates Q1 and pixel radius R1. Record the machine tool coordinates p2 of the cutting head at this time.

[0020] The pixel equivalent Dp of the camera calibration image is calculated based on R / R1. The pixel difference D1 and the actual distance D2 from the center of the circle to the center of the image are calculated based on the coordinates C1 of the circle center and Q1 of the image center.

[0021] Move the cutting head a distance D2 so that the CCD camera can capture a new camera calibration image, obtain the new center image coordinates C2 and pixel radius R2, and record the machine tool coordinates p3 of the cutting head at this time;

[0022] Based on the center image coordinates C1 and C2, and the machine tool coordinates p3 and p2, the accurate pixel equivalent Dp2 is calculated; based on the pixel equivalent Dp2, the new distance D3 from the center of the circle to the center of the image is calculated; based on the distance D3 and the machine tool coordinate p3, the machine tool coordinate p4 of the cutting head at this time is calculated, and the actual distance D4 from the center of the camera image to the center of the cutting head is obtained.

[0023] Based on the position of the CCD camera when it captures the image, the coordinates p5 of the cutting head machine are obtained, and the pixel distance D5 from the intersection point to the center of the camera image is obtained; based on the pixel distance D5 and the pixel equivalent Dp2, the actual distance D6 from the intersection point to the CCD camera is calculated.

[0024] Based on machine tool coordinates p5, distance D4, and distance D6, the machine tool coordinates p6 of the intersection point are calculated, and the machine tool coordinates p6 correspond to the precise edge position of the plate.

[0025] Furthermore, laser processing is performed on the edges of the sheet material, and the specific process includes the following:

[0026] Based on the machine tool coordinates corresponding to the intersection point, the initial deflection angle α of the sheet metal on the machine tool machining plane is determined;

[0027] The CCD camera is controlled to move along the end of the length direction of the plate to determine a new intersection point D, and the machine coordinates of the intersection point D are obtained according to the deflection angle α.

[0028] Based on the machine tool coordinates of the intersection point D, determine the equation of the straight line corresponding to the edge of the sheet metal and the actual deflection angle β of the sheet metal on the machine tool machining plane;

[0029] Based on the obtained straight line equation, calculate the machine tool coordinates of the corner points of the plate;

[0030] Based on the actual deflection angle β of the plate and the machine tool coordinates of the plate corners, the cutting head is controlled to perform laser processing on the plate.

[0031] Furthermore, the laser processing method also includes calibrating the monitoring camera to establish a mapping relationship between the monitoring image coordinates and the machine tool coordinates, and converting the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the mapping relationship; the specific calibration process includes the following steps:

[0032] Select the markers on the machine tool table and obtain the corresponding machine tool coordinates of the markers;

[0033] The marker image is captured by a surveillance camera, and the marker image coordinates are obtained by image processing.

[0034] The coordinates of the marker image are mapped to the coordinates of the marker machine tool, thus establishing a mapping relationship between the two.

[0035] Furthermore, the monitoring camera and the CCD camera are respectively mounted on the laser processing machine tool, with the CCD camera located on the cutting head.

[0036] Furthermore, the step of establishing a mapping relationship between the marker image coordinates and the marker machine tool coordinates specifically involves:

[0037] Based on the principle of perspective transformation, the coordinate transformation matrix of perspective transformation is obtained, and the mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool is established based on the coordinate transformation matrix.

[0038] The present invention also provides a laser processing system based on vision edge finding, the system comprising:

[0039] Initial positioning module: used to place the material to be processed on the processing table of the machine tool, and the monitoring camera performs initial positioning of the edge of the material to be processed and takes an initial image;

[0040] Image coordinate determination module: used to determine the edge points and corner points of the board based on the initial image, and obtain the corresponding monitoring image coordinates;

[0041] Coordinate transformation module: used to convert the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the established mapping relationship;

[0042] Precision positioning module: used to control the movement of the cutting head and CCD camera to the machine tool coordinates, and the CCD camera performs precision positioning of the edge of the material to be processed to obtain the precise edge position of the material;

[0043] Control processing module: Used to control the movement of the cutting head according to the edge position of the plate to perform laser processing on the plate to be processed.

[0044] Furthermore, it also includes a camera calibration module for calibrating the monitoring camera, establishing a mapping relationship between the monitoring image coordinates and the machine tool coordinates, and converting the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the mapping relationship; the camera calibration module includes:

[0045] Marker selection submodule: used to select markers on the machine tool processing table and obtain the corresponding machine tool coordinates of the markers;

[0046] Image processing submodule: Used to obtain the marker image from the surveillance camera and perform image processing on the marker image to obtain the marker image coordinates;

[0047] The mapping establishment submodule is used to establish a mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool based on the principle of perspective transformation.

[0048] Furthermore, the precise positioning module includes:

[0049] The movement control submodule is used to control the cutting head and CCD camera to move to the machine coordinates of the edge point and corner point, respectively.

[0050] Image acquisition submodule: Used to control the CCD camera to illuminate the edge of the board with a cross-shaped line laser light source. The cross-shaped light spots intersect with the adjacent edges of the board to capture CCD camera images.

[0051] Coordinate acquisition submodule: used to obtain the CCD camera image coordinates corresponding to the intersection of the cross-shaped light spot and the adjacent side of the plate, based on the CCD camera image;

[0052] Edge determination submodule: used to convert the CCD camera image coordinates into machine tool coordinates to obtain the precise edge position of the board.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] The laser processing method and system based on vision edge finding provided by this invention utilizes the cooperation of a monitoring camera and a CCD camera. Specifically, the monitoring camera performs initial positioning of the edge of the board, and then the CCD camera performs fine positioning of the edge of the board. This enables an adaptive edge finding process for boards of different lengths. The vision edge finding is more flexible and stable. The edge finding process does not rely entirely on the monitoring camera, avoiding the situation where the resolution is relatively small due to the large field of view of the monitoring camera, which would lead to insufficient accuracy. This improves the accuracy of repeated edge finding, avoids the risk of the cutting head hitting the board, and also improves the efficiency of laser processing. Attached Figure Description

[0055] To more clearly illustrate the solutions in this invention, a brief introduction to the accompanying drawings used in the description of the embodiments will be provided below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. Wherein:

[0056] Figure 1 This is a flowchart of the laser processing method based on visual edge finding according to the present invention.

[0057] Figure 2 This is a flowchart of the camera calibration process in this invention.

[0058] Figure 3 This is a flowchart of the CCD camera's precise positioning process in this invention.

[0059] Figure 4 This is a schematic diagram of the light spot used for precise positioning by the CCD camera in this invention.

[0060] Figure 5 This is a schematic diagram of the upper edge points and corner points of the material to be processed in this invention.

[0061] Figure 6 This is a flowchart of the CCD camera calibration process in this invention.

[0062] Figure 7 This is a flowchart of the laser processing performed by the cutting head in this invention.

[0063] Figure 8 This is a schematic diagram of the laser processing system based on vision edge finding according to the present invention.

[0064] Figure 9 This is a schematic diagram of the camera calibration module in this invention.

[0065] Figure 10 This is a schematic diagram of the precision positioning module in this invention.

[0066] Figure 11 This is a schematic diagram of the edge position determination module in this invention.

[0067] Figure 12 This is a schematic diagram of the control processing module in this invention. Detailed Implementation

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. For example, terms such as “length,” “width,” “upper,” “lower,” “left,” “right,” “front,” “rear,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” and “outer” indicate orientations or positions based on the orientations or positions shown in the accompanying drawings and are for ease of description only, and should not be construed as limiting the technical solution.

[0069] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this invention are intended to cover non-exclusive inclusion; the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a particular order. In the specification, claims, and accompanying drawings of this invention, when an element is referred to as "fixed to," "mounted to," "disposed of," or "connected to" another element, it may be directly or indirectly located on that other element. For example, when an element is referred to as "connected to" another element, it may be directly or indirectly connected to that other element.

[0070] Furthermore, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments.

[0071] It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0072] See Figure 1 As shown, the present invention provides a laser processing method based on visual edge finding, the specific steps of which include the following:

[0073] Step S1: Set up a monitoring camera and a CCD camera on the laser processing machine tool, with the CCD camera located on the cutting head.

[0074] Specifically, the monitoring camera is mounted on the protective cover of the machine tool and positioned diagonally above the CCD camera. The monitoring camera and the CCD camera adaptively locate the edge of the sheet metal to be processed, facilitating reliable laser processing.

[0075] Step S2: Calibrate the monitoring camera, establish the mapping relationship between the camera's image coordinates and the machine tool coordinates, and participate in... Figure 2 As shown, it specifically includes:

[0076] Step S21: Select the marker on the machine tool processing table and obtain the corresponding machine tool coordinates of the marker.

[0077] Specifically, the marker is generally a rectangular border, which corresponds to the four machine tool coordinates.

[0078] Step S22: The image of the marker is captured by the monitoring camera, and the image of the marker is processed to obtain the coordinates of the marker image.

[0079] Specifically, the image processing includes threshold segmentation, contour extraction, and target point localization, which can reliably obtain the coordinates of the marker image.

[0080] Step S23: Correspond one-to-one between the coordinates of the marker image and the coordinates of the marker machine tool. Based on the principle of perspective transformation, the coordinate transformation matrix of perspective transformation can be obtained, and the mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool can be established.

[0081] In this embodiment, the calibration process of the monitoring camera is actually to obtain a set of image coordinates and a set of machine tool coordinates respectively, and establish a mapping relationship between the image coordinates and the machine tool coordinates through the perspective transformation principle, so as to facilitate coordinate transformation during the edge finding process of the monitoring camera.

[0082] Step S3: Place the board to be processed on the processing table of the machine tool, and use a monitoring camera to take pictures of the edge of the board to obtain an initial image of the edge of the board, that is, to perform initial positioning of the edge of the board.

[0083] Step S4: Based on the initial image, determine the edge points and corner points of the board, and obtain the monitoring image coordinates corresponding to the edge points and corner points.

[0084] In this embodiment, since the monitoring camera can only capture a portion of the board material, the monitoring camera first performs preliminary positioning of the board material's edge to determine the edge points and corner points. Generally, for ease of operation, any edge point on the adjacent side of the lower right corner of the board material is selected, and the intersection of the adjacent sides is the corner point. This allows us to determine the approximate position on the board material where the CCD camera needs to be moved.

[0085] Step S5: Based on the established mapping relationship between the image coordinates of the monitoring camera and the machine tool coordinates, convert the monitoring image coordinates of the edge points and corner points into machine tool coordinates.

[0086] In this embodiment, the conversion accuracy of the monitoring image coordinates to machine tool coordinates can reach within 5mm. Since the field of view of the CCD camera is 50x50mm, the machine tool coordinates corresponding to the edge points and corner points initially located by the monitoring camera do not need to be very accurate. It is sufficient to ensure that they appear within the field of view of the CCD camera. After the CCD camera reaches these points, it will identify the precise machine tool coordinates corresponding to the edge points and corner points again through the recognition line laser.

[0087] Step S6: Control the cutting head and CCD camera to move to the machine tool coordinates, and use the CCD camera to precisely locate the edge of the material to be processed, thereby obtaining the accurate edge position of the material and completing the edge finding process of the material to be processed.

[0088] In step S6, the CCD camera performs precise positioning of the edge of the board material, such as... Figure 3The details shown include the following:

[0089] Step S61: Control the cutting head and CCD camera to move to the machine tool coordinates corresponding to the edge point and corner point, respectively;

[0090] Step S62: The CCD camera uses a cross-shaped laser light source to illuminate the edge of the board. The cross-shaped light spots intersect with the adjacent edges of the board to capture CCD camera images.

[0091] Step S63: Based on the CCD camera image, obtain the CCD camera image coordinates corresponding to the intersection point of the cross-shaped light spot and the adjacent side of the plate;

[0092] Specifically, such as Figure 4 As shown in the diagram, the intersection points of the laser source and the adjacent edges of the board are A1, A2, B, and C, respectively. Line segments A1B and A2C correspond to the edge positions of the board, and the intersection point of line segments A1B and A2C is corner point A of the board. Figure 5 As shown in the image.

[0093] Step S64: Convert the CCD camera image coordinates into machine tool coordinates to obtain the precise edge position of the board.

[0094] In step S64, the CCD camera image coordinates are converted to machine tool coordinates, i.e., the CCD camera is calibrated. (See [link to relevant documentation]). Figure 6 As shown, the specific process includes the following:

[0095] Step S641: The cutting head laser cuts a circle with a radius of R, and the cutting head stops at the coordinate position of the center of the circle, and the machine coordinates p1 of the center of the circle are recorded;

[0096] In this embodiment, calibration can also be performed by cutting other pre-defined patterns. Using a circle makes cutting easier and calibration more convenient.

[0097] Step S642: Move the cutting head so that the CCD camera can capture a complete circle to obtain the camera calibration image, and obtain the center image coordinates C1, the image center coordinates Q1 and the pixel radius R1. Record the machine tool coordinates p2 of the cutting head at this time.

[0098] Specifically, by moving the cutting head, the cut circle can be completely displayed in the field of view of the CCD camera, which facilitates the CCD camera to take pictures, recognize and locate the image to obtain the camera calibration image. This allows us to obtain the center image coordinates C1 of the circle on the camera calibration image, the image center coordinates Q1 of the camera calibration image, and the pixel radius R1 (i.e., the number of pixels corresponding to the circle radius).

[0099] Step S643: Calculate the pixel equivalent Dp based on R / R1, and calculate the pixel difference D1 and the actual distance D2 from the center of the circle C1 to the center of the image based on the coordinates of the center of the circle C1 and the coordinates of the center of the image Q1.

[0100] Specifically, the pixel equivalent Dp (mm / pixel) is the actual width or length of each pixel in the camera-calibrated image captured by the CCD camera; the pixel difference D1 is the pixel difference between the center image coordinates C1 and the image center coordinates Q1; and the actual distance from the center C1 to the image center D2 = D1 * Dp.

[0101] Step S644: Move the cutting head a distance D2 so that the CCD camera can capture a new camera calibration image, obtain the new center image coordinates C2 and pixel radius R2, and at the same time record the machine tool coordinates p3 of the cutting head at this time;

[0102] Specifically, by moving the cutting head a distance D2, the image center of the CCD camera will move to the vicinity of the circle's center. The CCD camera will then take a picture of the circle for recognition, obtaining a new camera calibration image.

[0103] Step S645: Based on the center image coordinates C1 and C2, and the machine tool coordinates p3 and p2, calculate a more accurate pixel equivalent Dp2; based on the pixel equivalent Dp2, calculate the distance D3 from the new center C2 to the camera image center; based on the distance D3 and the machine tool coordinates p3, calculate the machine tool coordinates p4 of the cutting head, and obtain the actual distance D4 from the camera image center to the cutting head center.

[0104] Specifically, the pixel equivalent Dp2 = (C2-C1) / (p3-p2), and the distance D3 = Dp2*(C2-Q1). The machine tool coordinates of the cutting head are p4 = p3+D3. At this time, the image center coincides with the center of the circle, and the actual distance from the camera image center to the cutting head center is D4 = p4-p1.

[0105] Step S646: Based on the position of the CCD camera when it captures the image, obtain the coordinates p5 of the cutting head machine tool and the pixel distance D5 from the intersection point to the center of the camera image. Based on the pixel distance D5 and the pixel equivalent Dp2, calculate the actual distance D6 from the intersection point to the CCD camera.

[0106] Specifically, in step S62, when the CCD camera captures an image, the machine coordinates of the CCD camera can be determined. Since the CCD camera is located on the cutting head, the machine coordinates p5 of the cutting head can be determined, and the pixel distance D5 from any point among the intersection points A1, A2, B, and C to the center of the camera image can be obtained. The actual distance D6 from the edge point to the CCD camera is D6 = D5 * Dp2.

[0107] Step S647: Based on the machine tool coordinates p5, distance D4, and distance D6, calculate the machine tool coordinates p6 of the intersection point. The machine tool coordinates p6 of the edge point correspond to the precise edge position of the material. The machine tool coordinates p6 of the edge point = p5 + D4 + D6.

[0108] In this embodiment, by repeating steps S646 and S647, the machine tool coordinates corresponding to multiple intersection points, namely intersection points A1, A2, B and C, can be obtained. Based on the machine tool coordinates of intersection points A1, A2, B and C, the precise position of the adjacent sides of the plate can be determined.

[0109] In this embodiment, the CCD camera precisely locates the edge of the material to be processed by using a cross-shaped line laser light source. This simplifies the complex background within the CCD camera's field of view. It only needs to detect the intersection of the cross-shaped light spot projected onto the surface of the material and the edge of the material to obtain the corresponding CCD camera image coordinates and convert them into machine tool coordinates. This completes the edge-finding process of the material, reducing the difficulty of image processing, increasing processing speed, and improving accuracy.

[0110] Step S7: Based on the precise edge position of the board obtained by the CCD camera, control the cutting head to move and complete the laser processing of the board to be processed.

[0111] Specifically, since the CCD camera is located on the cutting head, the coordinates and distance between the two on the laser processing machine tool are determined. After the CCD camera locates the precise edge position of the board, the position of the cutting head relative to the board can be determined, thereby controlling the movement of the cutting head to perform laser processing.

[0112] In step S7, the cutting head performs laser processing based on the edge position of the material. (See attached image.) Figure 7 As shown, the specific process includes the following:

[0113] Step S71: Based on the machine tool coordinates corresponding to the intersection point, continue referring to... Figure 5 As shown in the figure, the initial deflection angle α of the sheet metal to be processed on the machine tool processing plane is determined as shown in formula (1):

[0114] α=atan((B y -A1 y ) / (B x -A1 x ))180 / π(1)

[0115] Wherein, intersection points A1 and B are located on the edges corresponding to the length direction of the sheet metal, and intersection points A2 and C are located on the edges corresponding to the width direction of the sheet metal. The machine coordinates of intersection point B are (B x B yThe machine tool coordinates at intersection point A1 are (A1) x A1 y ).

[0116] Step S72: Control the CCD camera to move along the end of the length direction of the plate to obtain a new intersection point D.

[0117] Specifically, the cutting head moves the CCD camera along the length of the sheet material to intersection point D, which is located at 80% of the known length of the sheet material. Based on the sheet material length L, point A1, and the sheet material deflection angle α, the machine coordinates (D) of intersection point D are determined. X D y As shown in formula (2):

[0118]

[0119] In this embodiment, the intersection point D is mostly outside the field of view of the monitoring camera. The main purpose of selecting the intersection point D is for long sheet materials, because the production environment is relatively complex and the edges of the sheet material may not be flat. Therefore, selecting the edge point at the farthest possible location improves the edge finding accuracy. Specifically, the selection of the intersection point D can be adjusted according to actual needs. While ensuring the reliability of edge finding accuracy, and considering the field of view of the CCD camera, it is preferable to select the intersection point D at 80% of the sheet material length, which meets the requirements.

[0120] Step S73: Determine the equations of the two straight lines DA1 and CA2 passing through the origin A of the plate, that is, the equations of the straight lines corresponding to the adjacent sides of the plate, and calculate the actual deflection angle β of the plate to be processed on the machine tool processing plane.

[0121] Specifically, based on the machine tool coordinates of intersection point A1 and intersection point D, the equation y1 of line DA1 is determined, as shown in formula (3):

[0122]

[0123] Based on the machine tool coordinates of intersection point C and intersection point A2, determine the equation y2 of line CA2, as shown in formula (4):

[0124]

[0125] Based on the equation of the line y1, the actual deflection angle β is calculated as shown in formula (5):

[0126] β=atan(k1)180 / π (5).

[0127] In this embodiment, since the intersection point D is selected along the length direction and close to the end, line segment DA1 will be closer to the actual edge position of the board than line segment BA1. Therefore, the actual deflection angle β calculated based on line segment DA1 is also more accurate.

[0128] Step S74: Based on the intersection point of the two lines y1 and y2, calculate the machine coordinates of the corner point A of the plate, as shown in formula (6):

[0129]

[0130] Step S75: Based on the actual deflection angle β of the sheet metal and the machine tool coordinates of corner point A, laser processing is performed on the sheet metal according to the desired shape. In this embodiment, since the actual deflection angle and corner point machine tool coordinates of the sheet metal on the machine tool processing table are determined, the cutting head can process any shape on the sheet metal.

[0131] The vision-based edge-finding laser processing method provided in this embodiment involves setting up a monitoring camera and a CCD camera on the laser processing machine tool, and calibrating the monitoring camera to obtain the mapping relationship between image coordinates and machine tool coordinates. The monitoring camera is used to initially locate the edge of the sheet material, obtaining the edge points and corner points of the sheet material, and their corresponding machine tool coordinates. By controlling the movement of the CCD camera, the edge of the sheet material is precisely located, obtaining the accurate edge position. Based on the obtained edge position, the cutting head is controlled to complete the laser processing of the sheet material. This method, through the cooperation of the monitoring camera and the CCD camera, can reliably determine the accurate edge position of the sheet material, reducing dependence on the monitoring camera. The method is simple, reliable, and improves visual recognition accuracy, while also ensuring the precision of laser processing.

[0132] See Figure 8 As shown, this embodiment of the invention also provides a laser processing system based on vision edge finding, the system comprising:

[0133] Initial positioning module: used to place the material to be processed on the processing table of the machine tool, and the monitoring camera performs initial positioning of the edge of the material to be processed to obtain an initial image.

[0134] Image coordinate determination module: used to determine the edge points and corner points of the board based on the initial image, and obtain the corresponding monitoring image coordinates.

[0135] Coordinate transformation module: used to convert the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the established mapping relationship.

[0136] Precision positioning module: used to control the movement of the cutting head and CCD camera to the machine tool coordinates, and the CCD camera performs precision positioning of the edge of the material to be processed to obtain the precise edge position of the material.

[0137] Control processing module: Used to control the movement of the cutting head according to the edge position of the plate to perform laser processing on the plate to be processed.

[0138] For further details, please refer to [link / reference]. Figure 9 As shown, the system also includes a camera calibration module for calibrating the monitoring camera, establishing a mapping relationship between the monitoring image coordinates and the machine tool coordinates, and converting the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the mapping relationship; the camera calibration module includes:

[0139] Marker selection submodule: Used to select markers on the machine tool processing table and obtain the corresponding machine tool coordinates of the markers.

[0140] Image processing submodule: Used to obtain the marker image from the surveillance camera and perform image processing on the marker image to obtain the marker image coordinates.

[0141] The mapping establishment submodule is used to establish a mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool based on the principle of perspective transformation.

[0142] For further details, please refer to [link / reference]. Figure 10 As shown, the precision positioning module includes:

[0143] The movement control submodule is used to control the cutting head and CCD camera to move to the machine coordinates of the edge point and corner point, respectively.

[0144] Image acquisition submodule: Used to control the CCD camera to illuminate the edge of the board with a cross-shaped line laser light source. The cross-shaped light spots intersect with the adjacent edges of the board to capture CCD camera images.

[0145] Coordinate acquisition submodule: used to obtain the CCD camera image coordinates corresponding to the intersection of the cross-shaped light spot and the adjacent side of the plate, based on the CCD camera image;

[0146] Edge determination submodule: used to convert the CCD camera image coordinates into machine tool coordinates to obtain the precise edge position of the board.

[0147] For further details, please refer to [link / reference]. Figure 11 As shown, the edge determination submodule includes:

[0148] Laser cutting unit: Used to control the laser cutting radius R of the cutting head and stop at the center of the circle, and record the machine tool coordinates p1 of the cutting head;

[0149] Calibration image acquisition unit: used to move the cutting head so that the CCD camera can capture a complete circle to obtain the camera calibration image, and obtain the circle center image coordinates C1, image center coordinates Q1 and pixel radius R1, and record the machine tool coordinates p2 of the cutting head at this time;

[0150] Calibration parameter calculation unit: used to calculate the pixel equivalent Dp, pixel number difference D1, and actual distance D2 from the center of the circle to the center of the image of the camera calibration image;

[0151] New image acquisition unit: used to move the cutting head a distance D2 so that the CCD camera can capture a new camera calibration image, obtain the new center image coordinates C2 and pixel radius R2, and record the machine tool coordinates p3 of the cutting head at this time;

[0152] New parameter calculation unit: used to calculate the accurate pixel equivalent Dp2, the new distance from the center of the circle to the center of the image D3, the machine tool coordinates of the cutting head p4, and the actual distance from the center of the camera image to the center of the cutting head D4;

[0153] Edge parameter calculation unit: used to obtain the cutting head machine tool coordinates p5 based on the position when the CCD camera captures the CCD camera image, and to obtain the pixel distance D5 from the intersection point to the center of the camera image and the actual distance D6 from the intersection point to the CCD camera;

[0154] Edge coordinate determination unit: Based on machine coordinate p5, distance D4 and distance D6, the machine coordinate p6 of the intersection point is calculated, which corresponds to the precise edge position of the plate.

[0155] For further details, please refer to [link / reference]. Figure 12 As shown, the control processing module includes:

[0156] Preliminary Angle Determination Submodule: Used to preliminarily determine the angle α of the sheet metal on the machine tool machining plane based on the machine tool coordinates corresponding to the intersection point;

[0157] New intersection point determination submodule: Used to control the CCD camera to move along the end of the length direction of the material to determine the new intersection point D, and obtain the machine tool coordinates of the intersection point D according to the deflection angle α;

[0158] Parameter calculation submodule: used to determine the straight line equation corresponding to the edge of the plate and the actual deflection angle β of the plate on the machine tool processing plane based on the machine tool coordinates of the intersection point D;

[0159] Plate corner point determination submodule: used to calculate the machine coordinates of plate corner points based on the obtained straight line equation;

[0160] Laser processing submodule: Used to control the cutting head to perform laser processing on the material based on the actual deflection angle β of the material and the machine tool coordinates of the corner points of the material.

[0161] Specifically, the system provided in this embodiment of the invention is specifically used to execute the above-described method embodiments, and will not be described in detail again in this embodiment. The system provided in this embodiment of the invention uses both a CCD camera and a monitoring camera to identify the edge of the board material, which can obtain the precise edge position of the board material to be processed, and control the movement of the cutting head according to the edge position of the board material to complete the laser processing of the board material. This can ensure the accuracy of laser processing, further improve the efficiency of laser processing, and also ensure the safety of laser processing.

[0162] In this embodiment, the actual test data of the laser processing method and system based on vision edge finding provided by the present invention on the machine tool are shown in Table 1. The test was conducted at a machine tool traveling speed of 35 m / min. X and Y are the coordinates of the measured corner points of the sheet metal, the angle is the actual deflection angle β, and the maximum error is the repeatability error of multiple measurements.

[0163] Table 1

[0164]

[0165] As can be seen from Table 1, the error of the edge points and corner points of the board obtained by the present invention through visual edge finding is very small, that is, it can reliably obtain the precise edge position of the board, thereby ensuring the reliability and accuracy of laser processing.

[0166] The laser processing method and system based on vision edge finding provided by this invention avoids the difficulty of the monitoring camera in accurately identifying the precise edge position of the board due to the relatively complex recognition environment. By combining the monitoring camera and the CCD camera, the dependence on the monitoring camera is reduced, and the edge of the board can be reliably identified, thus improving the recognition accuracy. In the entire edge finding process, it is not necessary to manually move the cutting head onto the board as in sensor edge finding. Instead, it can automatically find the edge according to the process. Compared with sensor edge finding, it is more intelligent and truly achieves adaptive edge finding of the board.

[0167] Furthermore, compared to traditional sensor-based edge finding, visual edge finding is more flexible and stable, avoiding the risk of the cutting head hitting the plate, and can make up for the problem of low repeatability accuracy of sensor-based edge finding. It effectively solves the accuracy requirements of some customers for borderless cutting and improves processing efficiency.

[0168] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. 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 protection scope of the present invention.

Claims

1. A method of laser processing based on vision edge finding, characterized by: The specific steps of this method include the following: The sheet material to be processed is placed on the processing table of the machine tool, and the edge of the sheet material to be processed is initially positioned by the monitoring camera to obtain the initial image; Based on the initial image, the edge points and corner points of the board are determined, and the corresponding monitoring image coordinates are obtained; Based on the established mapping relationship between the image coordinates of the monitoring camera and the machine tool coordinates, the monitoring image coordinates of the edge points and corner points are converted into machine tool coordinates; The cutting head and CCD camera are controlled to move to the machine tool coordinates. The CCD camera precisely positions the edge of the sheet metal to be processed, obtaining the accurate edge position of the sheet metal. Specifically, the cutting head and CCD camera are controlled to move to the machine tool coordinates of the edge point and corner point, respectively. The CCD camera uses a cross-shaped linear laser light source to illuminate the edge of the sheet metal, with the cross-shaped light spot intersecting with the adjacent edges of the sheet metal, capturing CCD camera images. Based on the CCD camera images, the CCD camera image coordinates corresponding to the intersection points of the cross-shaped light spot and the adjacent edges of the sheet metal are obtained. The CCD camera image coordinates are converted into machine tool coordinates to obtain the accurate edge position of the sheet metal. Based on the edge position, the cutting head is controlled to move and perform laser processing on the material to be processed.

2. The laser processing method based on vision edge finding according to claim 1, characterized in that: The process of converting the CCD camera image coordinates into machine tool coordinates specifically includes the following steps: The cutting head laser cuts a circle of radius R and stops at the center of the circle. The machine coordinates p1 of the cutting head are recorded. Move the cutting head so that the CCD camera can capture a complete circle to obtain the camera calibration image, and obtain the circle center image coordinates C1, image center coordinates Q1 and pixel radius R1. Record the machine tool coordinates p2 of the cutting head at this time. The pixel equivalent Dp of the camera calibration image is calculated based on R / R1. The pixel difference D1 and the actual distance D2 from the center of the circle to the center of the image are calculated based on the coordinates C1 of the circle center and Q1 of the image center. Move the cutting head a distance D2 so that the CCD camera can capture a new camera calibration image, obtain the new center image coordinates C2 and pixel radius R2, and record the machine tool coordinates p3 of the cutting head at this time; Based on the center image coordinates C1 and C2, and the machine tool coordinates p3 and p2, the accurate pixel equivalent Dp2 is calculated; based on the pixel equivalent Dp2, the new distance D3 from the center of the circle to the center of the image is calculated; based on the distance D3 and the machine tool coordinate p3, the machine tool coordinate p4 of the cutting head at this time is calculated, and the actual distance D4 from the center of the camera image to the center of the cutting head is obtained. Based on the position of the CCD camera when it captures the image, the coordinates p5 of the cutting head machine are obtained, and the pixel distance D5 from the intersection point to the center of the camera image is obtained; based on the pixel distance D5 and the pixel equivalent Dp2, the actual distance D6 from the intersection point to the CCD camera is calculated. Based on machine tool coordinates p5, distance D4, and distance D6, the machine tool coordinates p6 of the intersection point are calculated, and the machine tool coordinates p6 correspond to the precise edge position of the plate.

3. The laser processing method based on vision edge finding according to claim 1, characterized in that: The process of controlling the cutting head to move according to the edge position to perform laser processing on the material to be processed includes the following: Based on the machine tool coordinates corresponding to the intersection point, the initial deflection angle α of the sheet metal on the machine tool machining plane is determined; The CCD camera is controlled to move along the end of the length direction of the plate to determine a new intersection point D, and the machine coordinates of the intersection point D are obtained according to the deflection angle α. Based on the machine tool coordinates of the intersection point D, determine the equation of the straight line corresponding to the edge of the sheet metal and the actual deflection angle β of the sheet metal on the machine tool machining plane; Based on the obtained straight line equation, calculate the machine tool coordinates of the corner points of the plate; Based on the actual deflection angle β of the plate and the machine tool coordinates of the plate corners, the cutting head is controlled to perform laser processing on the plate.

4. The laser processing method based on vision edge finding according to claim 1, characterized in that: The laser processing method further includes calibrating the monitoring camera to establish a mapping relationship between the monitoring image coordinates and the machine tool coordinates, and converting the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the mapping relationship; the specific calibration process includes the following steps: Select the markers on the machine tool table and obtain the corresponding machine tool coordinates of the markers; The marker image is captured by a surveillance camera, and the marker image coordinates are obtained by image processing. The coordinates of the marker image are mapped to the coordinates of the marker machine tool, thus establishing a mapping relationship between the two.

5. The laser processing method based on vision edge finding according to claim 4, characterized in that: The monitoring camera and the CCD camera are respectively installed on the laser processing machine tool, with the CCD camera located on the cutting head.

6. The laser processing method based on vision edge finding according to claim 4, characterized in that: The specific steps for establishing the mapping relationship between the marker image coordinates and the marker machine tool coordinates are as follows: Based on the principle of perspective transformation, the coordinate transformation matrix of perspective transformation is obtained, and the mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool is established based on the coordinate transformation matrix.

7. A laser processing system based on the laser processing method according to any one of claims 1-6, characterized in that: The system includes: Initial positioning module: used to place the material to be processed on the processing table of the machine tool, and the monitoring camera performs initial positioning of the edge of the material to be processed and takes an initial image; Image coordinate determination module: used to determine the edge points and corner points of the board based on the initial image, and obtain the corresponding monitoring image coordinates; Coordinate transformation module: used to convert the monitoring image coordinates of the edge points and corner points into machine tool coordinates; Precision positioning module: used to control the movement of the cutting head and CCD camera to the machine tool coordinates, and the CCD camera performs precision positioning of the edge of the material to be processed to obtain the precise edge position of the material; Control processing module: Used to control the movement of the cutting head according to the position of the edge of the board to perform laser processing on the board to be processed.

8. The laser processing system according to claim 7, characterized in that: It also includes a camera calibration module for calibrating the monitoring camera, establishing a mapping relationship between the monitoring image coordinates and the machine tool coordinates, and converting the monitoring image coordinates of the edge points and corner points into machine tool coordinates according to the mapping relationship; the camera calibration module includes: Marker selection submodule: used to select markers on the machine tool processing table and obtain the corresponding machine tool coordinates of the markers; Image processing submodule: Used to obtain the marker image from the surveillance camera and perform image processing on the marker image to obtain the marker image coordinates; The mapping establishment submodule is used to establish a mapping relationship between the coordinates of the marker image and the coordinates of the marker machine tool based on the principle of perspective transformation.

9. The laser processing system according to claim 8, characterized in that: The precise positioning module includes: The movement control submodule is used to control the cutting head and CCD camera to move to the machine coordinates of the edge point and corner point, respectively. Image acquisition submodule: Used to control the CCD camera to illuminate the edge of the board with a cross-shaped line laser light source. The cross-shaped light spots intersect with the adjacent edges of the board to capture CCD camera images. Coordinate acquisition submodule: used to obtain the CCD camera image coordinates corresponding to the intersection of the cross-shaped light spot and the adjacent side of the plate, based on the CCD camera image; Edge determination submodule: used to convert the CCD camera image coordinates into machine tool coordinates to obtain the precise edge position of the board.

Images