CN113828948B - Plate edge searching method, calibration system and edge searching system of laser cutting machine - Google Patents
Plate edge searching method, calibration system and edge searching system of laser cutting machine Download PDFInfo
- Publication number
- CN113828948B CN113828948B CN202111390157.6A CN202111390157A CN113828948B CN 113828948 B CN113828948 B CN 113828948B CN 202111390157 A CN202111390157 A CN 202111390157A CN 113828948 B CN113828948 B CN 113828948B
- Authority
- CN
- China
- Prior art keywords
- plate
- image data
- pixel
- calibration
- cross
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/70—Auxiliary operations or equipment
- B23K26/702—Auxiliary equipment
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/36—Removing material
- B23K26/38—Removing material by boring or cutting
Abstract
The invention provides a plate edge searching method and a plate edge searching system of a laser cutting machine, relates to the technical field of laser cutting, and is divided into a camera calibration part and a plate edge searching part. The camera, the light source and the protective cover are integrated; distortion correction is carried out on the camera; installing a vision suite at a proper position of the laser head; and automatic calibration is carried out, and the coordinate difference between the laser head and the camera, a small deviation angle caused in the installation process of the camera and a proportionality coefficient between the real world and the pixel world can be obtained through calibration. Moving a laser head to a mechanical origin position, taking a picture, calculating approximate coordinates of corner points of the plate, and moving a camera view center to a coordinate position; taking pictures, calculating accurate coordinates of corner points of the plate and the inclination angle of the plate, and moving a laser head to be right above the corner points of the plate; walk the frame and verify and seek limit precision, improve cutting accuracy, set up the corresponding position of laser head according to actual need, occupation space is littleer, and the installation is dismantled in a flexible way, and the protection targets in place.
Description
Technical Field
The invention relates to the technical field of laser cutting, in particular to a plate edge searching method, a calibration system and an edge searching system of a laser cutting machine.
Background
Laser cutting machines have developed at a rapid pace because of their high precision and efficiency. Generally, an edge searching operation is performed on a laser cutting machine before cutting a metal plate, and currently, two edge searching methods are mainly used: one is an edge finding method based on capacitance, and the other is an edge finding method based on vision.
When the capacitive edge searching method is adopted, if the breadth of the plate is large, the laser head needs to move a longer distance to complete the edge searching process, the time consumption is long, and the edge searching efficiency is low. If the size of the plate is set wrongly, the inclination of the plate is too large or the initial position of the laser head is not properly selected, mechanical damage can be caused, and certain potential safety hazards exist; the existing visual edge finding method mainly uses a template matching mode, the universality is low based on the template matching mode, characteristic matching points are required to be manually set for each plate with different thicknesses and different materials, a large amount of time is consumed for calibration test, and the efficiency is low.
Disclosure of Invention
The invention relates to a plate edge searching method, a calibration system and an edge searching system of a laser cutting machine, which are based on image data of a rectangular plate, acquire plate corner point coordinates and an inclination angle by image processing and data calculation, and control a laser head to perform the process of searching the edge of the plate by performing data interaction with an upper computer system.
The invention relates to three aspects which need protection.
The first aspect relates to a plate edge searching method of a laser cutting machine, which comprises the following steps:
s101, controlling a movable laser head to move to a mechanical origin position, and acquiring first image data of a preset pixel value;
s102, preprocessing the first image data, splitting the first image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks;
wherein the maximum area is identified as a plate, and the pixel block is defined as a first pixel block;
s103, setting a gray value of the first pixel block, scanning the first pixel block, and finding out a position where the first jump occurs, namely a pixel coordinate of the corner point of the plate;
s104, converting the pixel coordinates into the incremental information on the X, Y axis, moving the camera to the corner point of the plate according to the incremental information, shooting and shooting second image data;
s105, preprocessing the second image data, splitting the second image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the maximum area is identified as a plate, and the pixel block is defined as a second pixel block;
s106, setting a gray value of a second pixel block, scanning the second pixel block, finding a position where jumping occurs for the first time, and recording pixel coordinates;
s107, screening the coordinates of the second pixel block, fitting two edges of the plate, respectively calculating the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the inclination angle of the plate, and the intersection point of the two edges is the accurate angular point coordinates of the plate.
Further, step S102 further includes:
filtering the first image data and increasing the contrast; solving a first image data mean value, and carrying out self-adaptive edge sharpening according to the mean value;
performing binarization processing on the first image data;
performing morphological operation on the first image data based on the design structure element kernel; and then filtering and denoising the first image data.
Further, step S105 further includes:
filtering the second image data and increasing the contrast, solving the average value of the image data, and carrying out self-adaptive edge sharpening according to the average value;
carrying out binarization processing on the second image data; designing a structural element kernel, and performing morphological operation on the second image data; filtering and denoising the second image data;
for splitting the second image data into a plurality of pixel blocks, structural element kernels are designed, and morphological operations are respectively carried out on the second pixel blocks.
It is further noted that the method further comprises: verifying the edge searching precision;
starting image interface display, arranging a cross star at the right center of a window of the image interface, and inputting the size of a plate;
moving a camera to the right center of a window according to the coordinates and the inclination angle of the corner points of the plate, enabling the cross star to coincide with the corner points of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate;
precision information is obtained by observing the coincidence degree of the cross-shaped star and the plate edge, and preparation is made for the plate edge before cutting.
It should be further noted that in step S107, the actual tilt angle of the plate is determined by the offset angle k during the installation process of the camera1Compensation is performed.
Further, step S101 further includes, before:
s201, mounting a vision suite on a laser head;
s202, configuring a cross calibration plate;
s203, placing the cross calibration plate on a cutting plane, moving a laser head to the center of the cross calibration plate, and taking a picture to obtain image data;
s204, after moving a preset distance along the negative direction or the positive direction of the Y axis and the positive direction or the negative direction of the X axis, photographing the positive center position of the cross calibration plate to obtain image data, and taking the positive center position as a reference to obtain an interested area of the image data according to preset width data m and height data n;
s205, black cross pixel points of the interesting region are extracted, the center coordinates of the black cross are calculated based on the black cross pixel points, and deviation angles caused in the installation process of the vision suite are analyzed.
It is further noted that the method further comprises: carrying out binarization on the region of interest, extracting a complete black cross without impurity points, and setting four end point coordinate positions of the black cross
and calculating the center coordinate of the black cross based on the black cross pixel points, and analyzing the proportional coefficient of the real world and the pixel world and the coordinate difference of the laser head and the camera.
It should be further noted that if a horizontal or geometric deviation is caused during the installation of the camera, compensation is required, and the compensation angle is a deviation angle k1The calculation formula of (2) is as follows:
in a second aspect, the present invention further provides a calibration system for a laser cutting machine, where the calibration system includes: a laser head and a calibration control subsystem; a visual suite for shooting and shooting image data is arranged on the side of the laser head;
the calibration control subsystem comprises: the system comprises a region-of-interest configuration module, a calibration data processing module and a calibration calculation analysis module;
the region-of-interest configuration module, the calibration data processing module and the calibration calculation analysis module can be configured in a storage of the cutting machine, and can be called and used by a processor of the cutting machine when calibration is performed;
the interesting region configuration module is used for acquiring an interesting region by taking the right center position as a reference according to preset width data and height data;
the calibration data processing module is used for photographing the positive center position of the cross calibration plate to acquire central image data; moving the Y-axis preset distance along the positive direction or the negative direction of the Y-axis and moving the X-axis preset distance along the positive direction or the negative direction of the X-axis, photographing and obtaining black cross pixel points of the region of interest;
the calibration calculation analysis module is used for calculating the center coordinates of the black cross based on the black cross pixel points and analyzing the deviation angle caused in the installation process of the vision suite.
It is further noted that the arrangements
the center coordinates of the black cross calculated by the following formula are
，
Let A black cross center coordinate be
There is the formula:
the cross center coordinate of B can be obtained by the same method
Cross center coordinates of C
；
If horizontal or geometric deviations are caused during the camera installation process, compensation is required. The compensation angle, i.e. the deviation angle, being k1There is the formula:
in a third aspect, the present invention further provides an edge finding system of a laser cutting machine, where the edge finding system includes: the device comprises a mobile control module, an image acquisition module, an image processing module and a screening and fitting module;
the movement control module is used for controlling the movement of the movable laser head to the position of the mechanical origin, so that the image acquisition module acquires image data of a preset pixel value;
the image processing module is used for preprocessing the image data, dividing the image data into a plurality of pixel blocks and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the largest area is identified as a sheet;
setting a gray value of the image data, scanning the image data, and finding out a position where the first jump occurs, namely a pixel coordinate of the corner point of the plate; converting the pixel coordinates into the increment information on an X, Y axis, moving the camera to the corner point of the plate according to the increment information, shooting, capturing subsequent image data, finding out the position where the jump occurs for the first time, and recording the pixel coordinates;
the screening and fitting module is used for screening pixel coordinates, fitting out two edges of the plate, respectively solving the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the plate inclination angle, and the actual plate inclination angle is determined by using the deviation angle k in the camera installation process1Compensation is performed. The intersection points of the two sides are the angular point positions of the plate.
It should be further noted that the system further includes: a data preprocessing module;
the data preprocessing module is used for filtering the image data and increasing the contrast; solving the mean value of the image data, and carrying out self-adaptive edge sharpening according to the mean value; carrying out binarization processing on the image data; designing a structural element kernel, and performing morphological operation on image data; and then filtering and denoising the image data.
It should be further noted that the system further includes: an edge searching precision verification module;
the edge searching precision verification module is used for starting image interface display, arranging a cross star in the center of a window of the image interface and inputting the size of the plate;
moving a camera to the right center of a window according to the coordinates and the inclination angle of the plate, enabling the cross star to coincide with the angular point of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate;
and the edge searching precision is obtained through the contact ratio between the cross star and the plate edge.
According to the technical scheme, the invention has the following advantages:
the plate edge searching method, the calibration system and the edge searching system of the laser cutting machine provided by the invention have the advantage that the distortion of the camera is corrected, so that the cutting precision can be improved.
The camera is arranged on the cutting head, and can be arranged at the corresponding position of the laser head according to actual requirements, so that the camera has the advantages of smaller occupied space, flexible installation and disassembly and in-place protection.
In the calibrating and edge searching process, the edge searching time is short, and the problem of low edge searching efficiency caused by the fact that the edge searching process can be completed only by moving a laser head for a long distance due to large panel breadth in the prior art is solved.
The vision edge finding function adopted by the invention is stable within 2.8 seconds in single operation, namely, before the plate is cut every time, accurate cutting can be carried out in less than 2.8 seconds, and the cutting efficiency is improved.
In the precision of the method, the coordinates of the angular points of the plate are accurate to the sub-pixel level, and the inclination of the plate is accurate to within 0.1 degree.
The invention needs to install a vision suite at a proper position of a laser head for calibration and edge finding; and automatic calibration is carried out, and the coordinate difference between the laser head and the camera, a small deviation angle caused in the installation process of the camera and a proportionality coefficient between the real world and the pixel world can be obtained through calibration. The problems of mechanical damage and possible personnel injury caused by wrong size setting of the plate, overlarge gradient of the plate or improper initial position selection of the laser head are solved.
The calibration of the invention is to record parameters after the first calibration, and if the laser head and the camera do not need to be replaced, the calibration is not needed to be carried out after the subsequent use, thereby ensuring the cutting efficiency.
The invention enables the calibration and edge searching to be suitable for various devices and laser heads, meets the use of edge searching for plates with different thicknesses and different materials, does not need to manually set feature matching points, automatically runs and analyzes the corresponding angular points and plate edges by the system, and avoids the problem that the manual setting of the feature matching points consumes a large amount of time to carry out calibration test. The camera and the light source are separately arranged to form opposite placing spaces, so that the defect that the camera is damaged in the cutting process is avoided.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a flow chart of a calibration method provided by the present invention;
FIG. 2 is a schematic diagram of the position coordinates of the vision kit installed at the left side of the laser head;
FIG. 3 is a schematic view of the vision kit installed at the left side of the laser head;
FIG. 4 is a schematic diagram of the position coordinates of the vision kit installed at the right side of the laser head;
FIG. 5 is a schematic view of the vision kit installed in a right position on the laser head;
FIG. 6 is a flowchart of an edge-finding method according to the present invention;
FIG. 7 is a schematic view of a calibration system for a laser cutting machine;
fig. 8 is a schematic diagram of an edge finding system of the laser cutting machine.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Those of ordinary skill in the art will appreciate that the various exemplary elements and algorithm steps described in connection with the embodiments disclosed in the present invention as embodied in hardware, computer software, or a combination thereof may be embodied in electronic hardware, computer software, or combinations thereof, and that the various exemplary components and steps have been described in a functional general manner in the foregoing description for the purpose of illustrating the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the plate edge searching method and system of the laser cutting machine provided by the invention, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The invention provides a plate edge searching method and a plate edge searching system.
The invention mainly realizes the calibration and edge searching before the laser cutting, and aims to ensure the precision of the cutting process and improve the cutting quality.
Specifically, as shown in fig. 1, for the calibration method of the present invention, the integrated camera, the light source, and the protective cover are integrated into a whole to form a vision kit with a smaller overall size. The number of camera pixels involved in the present invention is over 600 ten thousand.
Before the edge searching is carried out, the integrated camera needs to be subjected to distortion removal operation by using a checkerboard. The checkerboard is composed of black squares and white squares with the side length of a preset length, the preset length can be 2cm, 4cm and the like, and specific data of the preset length are set according to actual conditions. The checkerboard may be 12 × 9 standard, or 16 × 10, etc., which is not limited herein.
Corresponding to the condition that checkerboard images at different angles and different positions are shot, all areas of the images are required to be distributed, all the squares in the checkerboard are shot clearly and visible in order to guarantee the effect of edge finding calibration, the number of shot images is required to be at least more than 20, and image data are input into distortion correction software for distortion correction.
S201, mounting a vision suite on a laser head; as shown in fig. 2 to 5, the vision kit of the present invention can be installed at a right position or a left position of the laser head. Here it is only the difference in relative position that has essentially no effect on the calibration.
S202, configuring a cross calibration plate;
for example, a black cross with a line width of about 3mm is designed, and a standard cross calibration plate is made with a white background.
S203, placing the cross calibration plate on a cutting plane, moving a laser head to the center of the cross calibration plate, and taking a picture to obtain image data;
s204, after moving a preset distance along the negative direction or the positive direction of the Y axis and the positive direction or the negative direction of the X axis, photographing the positive center position of the cross calibration plate to obtain image data, and taking the positive center position as a reference to obtain an interested area of the image data according to preset width data and height data;
for example, a calibration plate is placed on a cutting plane, a laser head is moved to the center of a cross of the calibration plate, a picture is taken and named as A, the calibration plate is moved in the negative direction of a Y axis by a preset distance, the calibration plate is taken and named as B, the calibration plate is moved in the positive direction of an X axis by a preset distance, the calibration plate is taken and named as C, the center of the cross of A, B, C is selected as an interested area, the size of the interested area is fixed, the width of the interested area is m, the height of the interested area is n, and the interested area is named as A1, B1 and C1 respectively.
S205, black cross pixel points of the interesting region are extracted, the center coordinates of the black cross are calculated based on the black cross pixel points, and deviation angles caused in the installation process of the vision suite are analyzed.
Specifically, for example, a1 is binarized to extract a complete black cross without any outliers, and the center coordinates of the four end points of the black cross are calculated. Is arranged as
let A black cross center coordinate be
There is the formula:
the cross center coordinate of B can be obtained by the same method
Cross center coordinates of C
。
If horizontal or geometric deviation is caused in the installation process of the camera, compensation is needed, and the supplementary angle, namely the deviation angle is k1There is the formula:
further, the center coordinates of the black cross are calculated based on the black cross pixel points, and the proportional coefficient of the real world and the pixel world and the coordinate difference of the laser head and the camera are analyzed.
After the calibration method is executed in the process, the edge searching method is carried out. The invention is not limited to the matching use of the calibration method and the edge searching method. The edge searching method defined by the invention can be used only by using a calibration method or only by using an edge searching method or by using a calibration method commonly used in the field according to the needs, or only by using the calibration method, and the edge searching mode can be not limited.
For the edge searching method provided by the invention, as shown in fig. 6:
s101, controlling a movable laser head to move to a mechanical origin position, and acquiring first image data of a preset pixel value;
s102, preprocessing the first image data, splitting the first image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the maximum area is identified as a plate, and the pixel block is defined as a first pixel block;
for the shot image, the image has more impurity interference, which affects the edge-searching judgment precision, and the invention filters the first image data and increases the contrast; solving a first image data mean value, and carrying out self-adaptive edge sharpening according to the mean value; performing binarization processing on the first image data; designing a structural element kernel, and performing morphological operation on the first image data; and then filtering and denoising the first image data.
For splitting the first image data into a plurality of pixel blocks, a structural element kernel is designed, and morphological operation is respectively carried out on the first pixel block.
S103, setting a gray value of the first pixel block, scanning the first pixel block, and finding out a position where the first jump occurs, namely a pixel coordinate of the corner point of the plate;
for the present invention, the first pixel block is the lower right corner of the plate, and is displayed by the gray value 255, and the gray value of the other area of the first image data is 0. Traversing the position of the jumping of the pixel from the lower left corner to the upper right corner of the first pixel block, wherein the position of the jumping for the first time is the pixel coordinate of the angular point of the plate.
S104, obtaining X, Y axis increment information according to the pixel coordinates, moving the camera to the corner point of the plate according to the increment information, shooting and shooting second image data; specifically, the incremental information on the X, Y axis is obtained according to the pixel coordinates and the coordinate difference between the laser head and the camera obtained in the calibration process.
Of course, the camera can be moved according to actual needs through the increment information on the X, Y axis to capture a plurality of subsequent image data.
S105, preprocessing the second image data, splitting the second image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the maximum area is identified as a plate, and the pixel block is defined as a second pixel block;
the invention filters the second image data and increases the contrast; solving the mean value of the image data, and carrying out self-adaptive edge sharpening according to the mean value; carrying out binarization processing on the second image data; designing a structural element kernel, and performing morphological operation on the second image data; and filtering and denoising the second image data.
For splitting the second image data into a plurality of pixel blocks, structural element kernels are designed, and morphological operations are respectively carried out on the second pixel blocks.
S106, setting a gray value of a second pixel block, scanning the second pixel block, finding a position where jumping occurs for the first time, and recording pixel coordinates;
for the second image data, the second pixel block is the lower right corner of the plate, and is displayed by the gray value 255, and the gray value of other areas of the image is 0. And traversing the position of the jump of the pixel from the lower right corner to the upper left corner of the image, and recording the coordinates of all the pixels.
S107, screening the coordinates of the second pixel block, fitting two edges of the plate, respectively calculating the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the plate inclination angle, and the actual plate inclination angle is determined by using the deviation angle k in the camera installation process1Compensation is performed. The intersection points of the two sides are the accurate corner coordinates of the plate.
This scheme still includes: verifying the edge searching precision; starting image interface display, arranging a cross star at the right center of a window of the image interface, and inputting the size of a plate;
moving a camera to the right center of a window according to the coordinates and the inclination angle of the corner points of the plate, enabling the cross star to coincide with the corner points of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate; rough precision information can be obtained by observing the overlapping degree of the cross star and the plate edge, and preparation is made for plate edge reservation before cutting. Of course, the user can observe the data at this point, or the system can automatically judge the data, for example, the system automatically judges that the data is patrolled for a circle along the edge of the plate, detects the deviation between the cross-shaped star and the edge of the plate, or the data of the contact ratio, and can give an alarm if the deviation exceeds a threshold value.
For the above-disclosed plate edge finding method of the laser cutting machine, the present invention further provides a calibration system of the laser cutting machine, as shown in fig. 7, the calibration system includes: a laser head and a calibration control subsystem; a visual suite for shooting and shooting image data is arranged on the side of the laser head;
the calibration control subsystem comprises: the system comprises a region-of-interest configuration module, a calibration data processing module and a calibration calculation analysis module;
the region-of-interest configuration module, the calibration data processing module and the calibration calculation analysis module can be configured in a storage of the cutting machine, and can be called and used by a processor of the cutting machine when calibration is performed.
The interesting region configuration module is used for acquiring an interesting region by taking the right center position as a reference according to preset width data and height data;
the calibration data processing module is used for photographing the positive center position of the cross calibration plate to acquire central image data; moving the Y-axis preset distance along the positive direction or the negative direction of the Y-axis and moving the X-axis preset distance along the positive direction or the negative direction of the X-axis, photographing and obtaining black cross pixel points of the region of interest;
the calibration calculation analysis module is used for calculating the center coordinates of the black cross based on the black cross pixel points and analyzing the deviation angle caused in the installation process of the vision suite.
As an embodiment of the calibration system, a vision suite is installed at the left side of a laser head, a black cross with the line width of about 3mm and a white background are designed, and a standard cross calibration plate is manufactured. The calibration control subsystem places the calibration plate on the cutting plane, moves the laser head to the center of the cross of the calibration plate, takes pictures and takes pictures, which are named as A; moving 80mm to the negative direction of the Y axis, taking pictures and naming the pictures as B; moving the X-axis forward direction by 80mm, taking a picture, and naming the picture as C.
The center of the cross at A, B, C was chosen as the region of interest, which was fixed in size and designated a1, B1, and C1, respectively.
Taking A1 as an example, firstly, binarization is carried out, a complete black cross without impurity points is extracted, 8 pixel points of the end points of the black cross can be found out through cyclic scanning, and the average value of adjacent pixel points is the central coordinates of four end points of the black cross and is set as the central coordinates of the four end points of the black cross
set the center coordinate of the black cross as
There is the formula:
the cross center coordinate of B can be obtained by the same method
Cross center coordinates of C
。
If horizontal or geometric deviations are caused during the camera installation process, compensation is required. The compensation angle, i.e. the deviation angle, being k1There is the formula:
and calculating a proportionality coefficient by using mapping data of the real world and the pixel world.
And calculating the coordinate difference between the laser head and the camera by using the mapping data and the proportionality coefficient of the real world and the pixel world.
By carrying out automatic calibration through the steps, a tiny deviation angle, a proportionality coefficient of a real world and a pixel world and a coordinate difference of a laser head and the camera caused in the installation process of the camera can be obtained.
The calibration of the invention is to record parameters after the first calibration, and if the laser head and the camera do not need to be replaced, the calibration is not needed to be carried out after the subsequent use, thereby ensuring the cutting efficiency.
Further, the invention also provides an edge searching system of the laser cutting machine, as shown in fig. 8,
the edge searching system comprises: the device comprises a mobile control module, an image acquisition module, an image processing module and a screening and fitting module;
the movement control module is used for controlling the movement of the movable laser head to the position of the mechanical origin, so that the image acquisition module acquires image data of a preset pixel value;
the image processing module is used for preprocessing the image data, dividing the image data into a plurality of pixel blocks and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the largest area is identified as a sheet;
setting a gray value of the image data, scanning the image data, and finding out a position where the first jump occurs, namely a pixel coordinate of the corner point of the plate; converting the pixel coordinates into the increment information on an X, Y axis, moving the camera to the corner point of the plate according to the increment information, shooting, capturing subsequent image data, finding out the position where the jump occurs for the first time, and recording the pixel coordinates;
the screening and fitting module is used for screening pixel coordinates, fitting out two edges of the plate, respectively solving the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the plate inclination angle, and the actual plate inclination angle is determined by using the deviation angle k in the camera installation process1Compensation is performed. The intersection points of the two sides are the angular point positions of the plate.
In order to reduce the interference of the interference pixel to the image information, the system of the invention also comprises a data preprocessing module;
the data preprocessing module is used for filtering the image data and increasing the contrast; solving the mean value of the image data, and carrying out self-adaptive edge sharpening according to the mean value; carrying out binarization processing on the image data; designing a structural element kernel, and performing morphological operation on image data; and then filtering and denoising the image data.
Further, the edge-searching system of the present invention further comprises: an edge searching precision verification module;
the edge searching precision verification module is used for starting image interface display, arranging a cross star in the center of a window of the image interface and inputting the size of the plate;
moving a camera to the right center of a window according to the coordinates and the inclination angle of the plate, enabling the cross star to coincide with the angular point of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate; and the edge searching precision is obtained through the contact ratio between the cross star and the plate edge.
The system automatically judges that the plate is patrolled for one circle along the edge of the plate, detects the deviation between the cross star and the plate edge or the contact ratio data, and can give an alarm for prompting if the deviation exceeds a threshold value.
The plate edge searching method and the plate edge searching system of the laser cutting machine realize the distortion correction of the camera, and can improve the cutting precision after the configuration on the camera is finished.
The camera is arranged on the cutting head, and can be arranged at the corresponding position of the laser head according to actual requirements, so that the camera has the advantages of smaller occupied space, flexible installation and disassembly and in-place protection.
In the calibrating and edge searching process, the edge searching time is short, and the problem of low edge searching efficiency caused by the fact that the edge searching process can be completed only by moving a laser head for a long distance due to large panel breadth in the prior art is solved.
The vision edge finding function adopted by the invention is stable within 2.8 seconds in single operation, namely, before the plate is cut every time, accurate cutting can be carried out in less than 2.8 seconds, and the cutting efficiency is improved.
In the precision of the method, the coordinates of the angular points of the plate are accurate to the sub-pixel level, and the inclination of the plate is accurate to within 0.1 degree.
The calibration of the invention is to record parameters after the first calibration, and if the laser head and the camera do not need to be replaced, the calibration is not needed to be carried out after the subsequent use, thereby ensuring the cutting efficiency.
The invention enables the calibration and edge searching to be suitable for various devices and laser heads, meets the use requirement of the edge searching process of plates with different thicknesses and different materials, does not need to manually set feature matching points, automatically runs and analyzes the corresponding angular points and plate edges by the system, and avoids the problem that the calibration test consumes a large amount of time when the feature matching points are manually set. The camera and the light source are separately arranged to form opposite placing spaces, so that the defect that the camera is damaged in the cutting process is avoided.
The invention avoids the problems of mechanical damage and possible personnel injury caused by wrong size setting of the plate, overlarge gradient of the plate or improper selection of the initial position of the laser head.
The edge finding method and system for a plate material of a laser cutting machine according to the present invention are the units and algorithm steps of each example described in connection with the embodiments disclosed herein, and can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (14)
1. A plate edge searching method of a laser cutting machine is characterized by comprising the following steps: mounting a vision suite on a laser head; the vision kit includes: a camera;
s101, controlling a movable laser head to move to a mechanical origin position, and acquiring first image data of a preset pixel value;
s102, preprocessing the first image data, splitting the first image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks;
wherein the maximum area is identified as a plate, and the pixel block is defined as a first pixel block;
s103, setting a gray value of the first pixel block, scanning the first pixel block, and finding out a position where jumping occurs for the first time in the first pixel block, namely a pixel coordinate of a plate corner point;
s104, obtaining X, Y axis increment information according to the pixel coordinate and the coordinate difference between the laser head and the camera obtained in the calibration process, converting the pixel coordinate into X, Y axis increment information, moving the camera to the corner point of the plate according to the increment information, shooting and shooting second image data;
s105, preprocessing the second image data, splitting the second image data into a plurality of pixel blocks, and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the maximum area is identified as a plate, and the pixel block is defined as a second pixel block;
s106, setting a gray value of a second pixel block, scanning the second pixel block, finding a position where jumping occurs for the first time in the second pixel block, and recording pixel coordinates;
traversing the position of the jump of the pixel from the lower right corner to the upper left corner of the image, and recording the coordinates of all the pixels;
s107, screening the coordinates of the second pixel block, fitting two edges of the plate, respectively calculating the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the inclination angle of the plate, and the intersection point of the two edges is the accurate angular point coordinates of the plate.
2. The edge finding method for a plate material of a laser cutting machine according to claim 1,
step S102 further includes:
filtering the first image data and increasing the contrast; solving a first image data mean value, and carrying out self-adaptive edge sharpening according to the mean value;
performing binarization processing on the first image data;
performing morphological operation on the first image data based on the design structure element kernel; and then filtering and denoising the first image data.
3. The edge finding method for a plate material of a laser cutting machine according to claim 1 or 2,
step S105 further includes:
filtering the second image data and increasing the contrast, solving the mean value of the second image data, and carrying out self-adaptive edge sharpening according to the mean value;
carrying out binarization processing on the second image data; designing a structural element kernel, and performing morphological operation on the second image data; filtering and denoising the second image data;
for splitting the second image data into a plurality of pixel blocks, structural element kernels are designed, and morphological operations are respectively carried out on the second pixel blocks.
4. The edge finding method for a plate material of a laser cutting machine according to claim 1 or 2,
the method further comprises the following steps: verifying the edge searching precision;
starting image interface display, arranging a cross star at the right center of a window of the image interface, and inputting the size of a plate;
moving a camera according to the coordinates and the inclination angle of the corner points of the plate, enabling the cross stars to coincide with the corner points of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate;
precision information is obtained by observing the coincidence degree of the cross-shaped star and the plate edge, and preparation is made for the plate edge before cutting.
5. The edge finding method for a plate material of a laser cutting machine according to claim 1 or 2,
step S107, the actual plate inclination angle utilizes the deviation angle k in the camera installation process1Compensation is performed.
6. The plate edge searching method of the laser cutting machine according to claim 1 or 2, wherein step S101 is preceded by:
s202, configuring a cross calibration plate;
s203, placing a cross calibration plate on a cutting plane, moving a laser head to the center of the cross calibration plate, and taking a picture to obtain image data named A;
s204, moving the laser head by a preset distance along the negative direction of the Y axis, and photographing the positive center position of the cross calibration plate to obtain image data named as B; moving the cross calibration plate for a preset distance along the positive direction of the X axis, and photographing the positive center position of the cross calibration plate to obtain image data named as C; selecting A, B, C cross center as interested area, with fixed area size, width m, height n, respectively named as A1, B1 and C1; acquiring an interested area of the image data according to preset width data and height data by taking the center position as a reference;
s205, black cross pixel points of the interesting region are extracted, the center coordinates of the black cross are calculated based on the black cross pixel points, and deviation angles caused in the installation process of the vision suite are analyzed.
7. The edge finding method for a plate material of a laser cutting machine according to claim 6,
the method further comprises the following steps: carrying out binarization on the region of interest, extracting a complete black cross without any impurity point, and setting four end point coordinates of the black cross of the region of interest A1 as
let A black cross center coordinate be
There is the formula:
8. the edge finding method for a plate material of a laser cutting machine according to claim 7,
and calculating the center coordinate of the black cross based on the black cross pixel points, and analyzing the proportional coefficient of the real world and the pixel world and the coordinate difference of the laser head and the camera.
9. The edge finding method for a plate material of a laser cutting machine according to claim 7,
if geometric deviation is caused in the installation process of the camera, compensation is needed, and the compensation angle is the deviation angle k1The calculation formula of (2) is as follows:
10. a calibration system of a laser cutting machine, characterized in that the calibration system adopts the plate edge searching method of the laser cutting machine according to any one of claims 1 to 9;
the calibration system comprises: a laser head and a calibration control subsystem; a visual suite for shooting and shooting image data is arranged on the side of the laser head;
the calibration control subsystem comprises: the system comprises a region-of-interest configuration module, a calibration data processing module and a calibration calculation analysis module;
configuring an interested region configuration module, a calibration data processing module and a calibration calculation analysis module into a storage of the cutting machine, and calling and using by a processor of the cutting machine when calibration is executed;
the interesting region configuration module is used for acquiring an interesting region by taking the right center position as a reference according to preset width data and height data;
the calibration data processing module is used for photographing the positive center position of the cross calibration plate to obtain center image data which is named as A; moving the laser head by a preset distance along the positive direction or the negative direction of the Y axis, and photographing the positive center position of the cross calibration plate to obtain image data named as B;
moving the X axis along the positive direction or the negative direction of the X axis by a preset distance, and photographing the positive center position of the cross calibration plate to obtain image data named as C; acquiring black cross pixel points of the region of interest;
the calibration control subsystem selects cross centers of A, B and C as interested areas, the sizes of the areas are fixed, the width is m, the height is n, and the centers are respectively named as A1, B1 and C1;
the calibration calculation analysis module is used for calculating the center coordinates of the black cross based on the black cross pixel points and analyzing the deviation angle caused in the installation process of the vision suite.
11. The calibration system for a laser cutting machine according to claim 10,
configuration of
the black cross center coordinates of the region of interest A1 are calculated by the following formula
，
Let A black cross center coordinate be
There is the formula:
the cross center coordinate of B can be obtained by the same method
Cross center coordinates of C
；
If horizontal or geometric deviation is caused in the installation process of the camera, compensation is needed; the compensation angle, i.e. the deviation angle, being k1There is the formula:
12. an edge searching system of a laser cutting machine, characterized in that the edge searching system adopts the plate edge searching method of the laser cutting machine according to any one of claims 1 to 9;
the edge searching system comprises: the device comprises a mobile control module, an image acquisition module, an image processing module and a screening and fitting module;
the movement control module is used for controlling the movement of the movable laser head to the position of the mechanical origin, so that the image acquisition module acquires image data of a preset pixel value;
the image processing module is used for preprocessing the image data, dividing the image data into a plurality of pixel blocks and sequencing the pixel blocks based on the areas occupied by the pixel blocks; wherein the largest area is identified as a sheet;
setting a gray value of the image data, scanning the image data, and finding out a position where the first jump occurs, namely a pixel coordinate of the corner point of the plate; converting the pixel coordinates into the increment information on an X, Y axis, moving the camera to the corner point of the plate according to the increment information, shooting, capturing subsequent image data, finding out the position where the jump occurs for the first time, and recording the pixel coordinates;
screeningThe fitting module is used for screening pixel coordinates, fitting out two edges of the plate, respectively calculating the slopes of the two edges, converting the slopes into angles, wherein the average value of the two angles is the plate inclination angle, and the actual plate inclination angle utilizes the deviation angle k in the camera installation process1And (5) compensating, wherein intersection points at two sides are the angular point positions of the plate.
13. The edge-finding system of a laser cutting machine according to claim 12,
further comprising: a data preprocessing module;
the data preprocessing module is used for filtering the image data and increasing the contrast; solving the mean value of the image data, and carrying out self-adaptive edge sharpening according to the mean value; carrying out binarization processing on the image data; designing a structural element kernel, and performing morphological operation on image data; and then filtering and denoising the image data.
14. The edge-finding system of a laser cutting machine according to claim 12,
further comprising: an edge searching precision verification module;
the edge searching precision verification module is used for starting image interface display, arranging a cross star in the center of a window of the image interface and inputting the size of the plate;
moving a camera according to the coordinates and the inclination angle of the plate, enabling the cross star to coincide with the angular point of the plate, then carrying out a frame walking action, and patrolling for a circle along the edge of the plate;
and the edge searching precision is obtained through the contact ratio between the cross star and the plate edge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111390157.6A CN113828948B (en) | 2021-11-23 | 2021-11-23 | Plate edge searching method, calibration system and edge searching system of laser cutting machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111390157.6A CN113828948B (en) | 2021-11-23 | 2021-11-23 | Plate edge searching method, calibration system and edge searching system of laser cutting machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113828948A CN113828948A (en) | 2021-12-24 |
| CN113828948B true CN113828948B (en) | 2022-03-08 |
Family
ID=78971580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111390157.6A Active CN113828948B (en) | 2021-11-23 | 2021-11-23 | Plate edge searching method, calibration system and edge searching system of laser cutting machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113828948B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117161589B (en) * | 2023-09-21 | 2024-04-12 | 昆山市金康电子有限公司 | Intelligent detection method and system for marking deviation of laser engraving machine |
| CN117226250B (en) * | 2023-11-13 | 2024-03-15 | 大族激光智能装备(江苏)有限公司 | Processing positioning method, processing positioning device and computer readable storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750691B (en) * | 2012-05-29 | 2014-08-06 | 重庆大学 | Corner pair-based image registration method for Cauchy-Schwarz (CS) divergence matching |
| CN108230400B (en) * | 2017-12-26 | 2021-10-19 | 常州固高智能控制技术有限公司 | Self-adaptive coordinate reconstruction method suitable for laser cutting machine |
| JP2019179342A (en) * | 2018-03-30 | 2019-10-17 | 日本電産サンキョー株式会社 | Image processing device and image processing method |
| CN108747049B (en) * | 2018-06-14 | 2020-04-10 | 苏州大族松谷智能装备股份有限公司 | Implementation method of laser cutting machine for positioning plate by using CCD |
| CN109612390B (en) * | 2018-12-17 | 2019-11-08 | 江南大学 | Large-size workpiece automatic measuring system based on machine vision |
| CN110599546A (en) * | 2019-08-28 | 2019-12-20 | 贝壳技术有限公司 | Method, system, device and storage medium for acquiring three-dimensional space data |
| CN112767359B (en) * | 2021-01-21 | 2023-10-24 | 中南大学 | Method and system for detecting corner points of steel plate under complex background |
| CN113298834B (en) * | 2021-04-29 | 2022-07-05 | 华工法利莱切焊系统工程有限公司 | Visual edge finding image processing method and device for metal plate |
| CN113538583A (en) * | 2021-07-28 | 2021-10-22 | 柔胜刚智能科技(苏州)有限公司 | Method for accurately positioning position of workpiece on machine tool and vision system |
-
2021
- 2021-11-23 CN CN202111390157.6A patent/CN113828948B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113828948A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113828948B (en) | Plate edge searching method, calibration system and edge searching system of laser cutting machine | |
| CN109100363B (en) | Method and system for distinguishing defects of attached foreign matters from dust | |
| CN101753775B (en) | Imaging device | |
| US7019713B2 (en) | Methods and measurement engine for aligning multi-projector display systems | |
| CN103716594B (en) | Panorama splicing linkage method and device based on moving target detecting | |
| CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
| CN109977907B (en) | Expense reimbursement method and system based on bill recognition | |
| CN106677037B (en) | Portable asphalt pavement disease detection method and device based on machine vision | |
| CN107356213B (en) | Optical filter concentricity measuring method and terminal equipment | |
| CN109495729B (en) | Projection picture correction method and system | |
| CN107024485A (en) | The defect inspection method and device of camber display screen | |
| CN108986129B (en) | Calibration plate detection method | |
| CN103955916A (en) | Automobile panorama camera calibration method and apparatus | |
| CN111025701A (en) | Curved surface liquid crystal screen detection method | |
| EP3617937A1 (en) | Image processing device, driving assistance system, image processing method, and program | |
| CN115384052A (en) | Intelligent laminating machine automatic control system | |
| CN106989681A (en) | The dimension measurement method and measuring apparatus of a kind of via | |
| CN113375555A (en) | Power line clamp measuring method and system based on mobile phone image | |
| CN110376218B (en) | Method and device for detecting residual image of display panel | |
| CN208863001U (en) | Optical projection system | |
| CN115684012A (en) | Visual inspection system, calibration method, device and readable storage medium | |
| CN108230385B (en) | Method and device for detecting number of ultra-high laminated and ultra-thin cigarette labels by single-camera motion | |
| CN206583440U (en) | A kind of projected image sighting distance detecting system | |
| CN112839168B (en) | Method for automatically adjusting camera imaging resolution in AOI detection system | |
| CN113160155A (en) | Method and device for determining highest point of auxiliary spacer, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |