CN115722498B - Mold visual identification laser cleaning equipment and visual identification positioning method - Google Patents
Mold visual identification laser cleaning equipment and visual identification positioning method Download PDFInfo
- Publication number
- CN115722498B CN115722498B CN202211453831.5A CN202211453831A CN115722498B CN 115722498 B CN115722498 B CN 115722498B CN 202211453831 A CN202211453831 A CN 202211453831A CN 115722498 B CN115722498 B CN 115722498B
- Authority
- CN
- China
- Prior art keywords
- die
- laser
- clamping table
- operator
- clamping
- 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
Landscapes
- Moulds For Moulding Plastics Or The Like (AREA)
Abstract
The invention provides a die visual identification laser cleaning device and a visual identification positioning method, wherein the device comprises a die clamping module with double-station switching and a laser visual module, the die clamping module is used for clamping dies, the former die is used for feeding at a feeding station when the former die is subjected to laser operation at a processing station, the laser visual module is used for identifying the specific outline shape of the die so as to generate a corresponding scanning area, and meanwhile, the device is used for acquiring the distance between the surface of the die and the laser visual module and controlling the distance of laser processing to be in a focal depth range. The invention can automatically complete the procedures of positioning, processing domain identification, high-precision automatic cleaning and the like of the die on the basis of highly combining equipment and algorithm programs, realizes high-efficiency automatic cleaning of the die, and obviously improves the cleaning efficiency and precision.
Description
Technical Field
The invention relates to the technical field of mold cleaning, in particular to a mold visual identification laser cleaning device and a visual identification positioning method.
Background
The mould is a manufacturing device for realizing one-time forming of parts with different materials and different molded surfaces. However, after the part is formed, special plastics, metals, other composite materials and the like in different parts are solidified on the surface of the die, so that sundries solidified on the surface of the die need to be cleaned timely, and the forming precision of subsequent parts can be influenced. The precision of the surface of the die determines the precision of the surface of the formed part, so that the cleaning efficiency and the cleaning thoroughness of sundries are ensured in the cleaning process, and the precision of the surface of the die is ensured not to be damaged. The traditional cleaning method is mostly manual cleaning, and adopts silk floss pulling, polishing, chemical reagent or the like to remove impurities. But the manual cleaning efficiency is low, the multiple processing uniformity is poor, the cleaning is not thorough enough, the manual cooking degree and skill requirements are very high, the time and labor are wasted, the processing requirements are difficult to reach, and the current high-efficiency high-precision automatic processing requirement is not met.
Disclosure of Invention
The purpose of the invention is that: in order to overcome the defects in the prior art, the device capable of visually identifying and automatically cleaning the die is provided.
In order to achieve the above purpose, the invention provides a die visual identification laser cleaning device, which comprises a die clamping module with double-station switching and a laser visual module, wherein the die clamping module is used for clamping dies, the former die is used for feeding at a feeding station when the former die is subjected to laser operation at a processing station, and the laser visual module is used for identifying the specific contour shape of the die so as to generate a corresponding scanning area, and meanwhile, is used for acquiring the distance between the surface of the die and the laser visual module and controlling the distance of laser processing to be in a focal depth range.
Further, the die clamping module comprises a base, a first clamping table and a second clamping table, wherein the first clamping table and the second clamping table are arranged on the base and used for clamping the die, the first clamping table is movably connected with the base through a first guide assembly, the second clamping table is movably connected with the base through a second guide assembly, the first clamping table is in driving connection with a first driving assembly on the base, and the second clamping table is in driving connection with a second driving assembly on the base.
Further, the first guide assembly comprises a first guide rail and a first sliding block, the first guide rail is arranged on the supporting plates on two sides of the base, and the first sliding block is arranged on the lower surface of the first clamping table and is in sliding connection with the first guide rail; the second guide assembly comprises a second guide rail and a second slide block, the second guide rail is arranged on the base and positioned between the two support plates, the second slide block is arranged on the lower surface of the support table and is in sliding connection with the second guide rail, and the second clamping table is connected with the support table through the lifting guide assembly and the lifting driving assembly.
Further, the first driving assembly comprises a screw rod rotatably arranged on the supporting plate, the screw rod is in transmission connection with the first motor, the first clamping table is provided with a first connecting block, and the first connecting block is provided with a threaded hole and is in threaded fit with the screw rod; the second driving assembly comprises a driving belt wheel and a driven belt wheel which are arranged on the supporting block in a rotating mode, the driving belt wheel is connected with the driven belt wheel through a synchronous belt, a second connecting block is arranged on the supporting table and connected with the synchronous belt, a third connecting block is further arranged on the first clamping table and connected with the synchronous belt, power of the first motor is transmitted to the synchronous belt, and the second connecting block and the third connecting block are respectively connected with a lower layer portion and an upper layer portion of the synchronous belt.
Further, the lifting guide assembly comprises a linear bearing arranged on the supporting table and a linear guide rod arranged on the second clamping table, and the linear guide rod is in sliding fit with the linear bearing.
Further, the lifting driving assembly comprises a lifting air cylinder arranged on the supporting table, and a piston rod of the lifting air cylinder is connected with the lower surface of the second clamping table.
Further, balls are uniformly distributed on the first clamping table and the second clamping table, and the balls are used for rolling support during die installation; the first clamping table and the second clamping table are provided with guide wheels and locking mechanisms, the guide wheels are rotatably connected with the first clamping table and the second clamping table, the guide wheels are arranged at two adjacent side edges of the die positioning position, and the locking mechanisms are arranged on one side opposite to the guide wheels and used for tightly pushing the die.
Further, the laser vision module comprises a portal frame erected above the base, and a vision recognition assembly and a laser processing assembly which are arranged on the portal frame;
the laser processing assembly comprises a laser input optical fiber, a vibrating mirror and a field lens, wherein the laser input optical fiber is used for inputting laser emitted by a laser, the vibrating mirror and the field lens deflect and focus laser generated by the laser, the laser processing assembly further comprises a Z-axis sliding table, a mounting seat on the Z-axis sliding table is provided with the laser input optical fiber, the vibrating mirror and the field lens, and a distance sensor is further arranged on the mounting seat and is used for measuring the distance between the surface of a die and the field lens;
the visual recognition component comprises a visual camera and a visual adjusting mechanism connected with the visual camera, wherein the visual adjusting mechanism is provided with a plurality of adjusting degrees of freedom and is connected with the mounting seat so as to adjust the position of the visual camera relative to laser, and an X-axis sliding table is further arranged on the portal frame and connected with the X-axis sliding table.
The invention also provides a mould visual identification positioning method, which comprises the following steps:
s1, acquiring image data placed by a die by using a vision camera;
s2, extracting image data, extracting the edge of the die by adopting a Sobel operator, obtaining the center coordinates and the edge length of the edge of the die by adopting a Gaussian filtering algorithm, and judging the model of the die;
s3, after the model is established for the mold, identifying the peripheral outline of the mold according to the image data, and transmitting the identified outline data to control software;
and S4, controlling the laser processing assembly to perform laser scanning processing according to the identified profile data.
Further, S2 specifically includes the following sub-steps:
s21, scanning each pixel in the image by using a template, replacing the value of a central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template, smoothing the image by Gaussian, and convolving the pixel function f (x, y) of the original mold image by using a Gaussian filter G (x, y) to obtain a smoothed I (x, y), wherein the expression is as follows:
I(x,y)＝G(x,y)*f(x,y)；
s22, calculating gradient amplitude and direction of the image I (x, y) by adopting a Sobel operator, and calculating G (x) and G (y) by convolving the image I (x, y) with a Sobel horizontal operator and a Sobel vertical operator:
G(x)＝I(x,y)*Sobel x (x,y)
G(y)＝I(x,y)*Sobel y (x,y)
wherein Sobel x (x, y) is a horizontal operator, sobel y (x, y) is a vertical operator, and the values are respectively:
the amplitude M (x, y) of the image gradient is further obtained as:
the angle α (x, y) is:
s23, global threshold segmentation is carried out on the graph processed by the sobel operator, the adopted operator is threshold, specific parameters are adjusted according to different graphs, a curve is segmented into a plurality of unconnected areas according to the given parameters, and after connection operator processing, the unconnected areas are distinguished by different colors;
s24, screening target straight lines, acquiring data, selecting given limiting conditions to obtain targets, adopting a select_shape operator in the process, selecting regions by the operator select_shape according to the shapes, and calculating the indicated characteristics for each input region from the regions. If each or at least one of the calculated features is within a default limit, the region is adapted to output, a key line segment for distinguishing the mold is finally obtained, the length of the line segment is obtained by using a connlength operator, and the model of the mold is determined;
s25, acquiring contour data of a die; firstly, modifying parameters on the basis of S23 by using a threshold operator and a connection operator, removing some irrelevant areas by using a select_shape operator, and obtaining a diagonal segment or a curved segment on a mould by using a start_region, a count_obj and a select_obj operator to finally obtain a data value of a mould contour; and transmitting the obtained profile data to software to form a corresponding shape scanning file, and naming the corresponding shape scanning file as a specific model.
The scheme of the invention has the following beneficial effects:
on the basis of high combination of equipment and algorithm programs, the die is automatically conveyed to a processing station after initial positioning, the region to be processed can be automatically identified, the focal length can be adjusted, then laser is controlled to carry out cleaning processing, most substances can be stripped by means of accurate die identification and positioning and high-energy characteristics of the laser, the processing precision can be greatly improved without damaging body materials outside the processing region, in a word, the processes of positioning, processing region identification, high-precision automatic cleaning and the like of the die can be automatically completed, high-efficiency automatic cleaning of the die is realized, and the cleaning efficiency and precision are remarkably improved.
Other advantageous effects of the present invention will be described in detail in the detailed description section which follows.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the present invention;
FIG. 2 is a schematic diagram of a mold clamping module according to the present invention;
FIG. 3 is a schematic view of a mold clamping module according to the present invention (another view);
FIG. 4 is a schematic diagram of a laser vision module according to the present invention;
FIG. 5 is a schematic diagram of a mold and features to be identified in an embodiment of the invention;
FIG. 6 shows the left target straight line and the straight line length obtained in the embodiment of the present invention;
FIG. 7 shows the upper right diagonal and tilt angle obtained in the embodiment of the present invention;
FIG. 8 is a profile of a mold to be machined identified in an embodiment of the present invention.
[ reference numerals description ]
1-a base; 2-a die; 3-a first clamping table; 4-a second clamping table; 5-a first guide rail; 6-a first slider; 7-supporting plates; 8-a second guide rail; 9-a second slider; 10-supporting table; 11-screw rod; 12-a first motor; 13-a first connection block; 14-a driving pulley; 15-a driven pulley; 16-a third connection block; 17-synchronous belt; 18-a second connection block; 19-a linear bearing; 20-a linear guide rod; 21-lifting air cylinders; 22-avoiding grooves; 23-balls; 24-guiding wheels; 25-a locking mechanism; 26-portal frames; 27-a laser input fiber; 28-vibrating mirror; 29-field lens; a 30-Z axis sliding table; 31-a mounting base; a 32-distance sensor; 33-a vision camera; 34-visual adjustment mechanism; 35-X axis slipway.
Detailed Description
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are merely some, but not all embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concepts of the disclosure by way of illustration, and only the components related to the disclosure are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated. In addition, in the following description, specific details are provided in order to provide a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
As shown in fig. 1, the embodiment of the present invention provides a mold visual recognition laser cleaning device, which is a dual-station switching mold pulse laser efficient high-precision intelligent cleaning device (wherein the mold includes, but is not limited to, plastics, composite materials, adhesives, metal surface oxidation waiting removals, all substances which can be removed according to high-energy laser ablation are regarded as a mold and can be processed on the device), and comprises a dual-station switching mold clamping module and a laser visual module. The die clamping module has the function of double-station switching, the former die is used for feeding at the feeding station when the processing station is used for laser operation, and the working efficiency of the equipment is guaranteed. The laser vision module can identify the specific outline shape of the processed die, then a corresponding scanning area is generated in the control software of the industrial personal computer, meanwhile, the distance between the die surface and the laser vision module can be acquired, and the distance of laser processing is controlled and ensured to be in the focal depth range.
Meanwhile, as shown in fig. 2 and 3, in the present embodiment, the mold clamping module includes a base 1, and the double-station switching finger is disposed on the base 1 and clamps a first clamping table 3 and a second clamping table 4 of the mold 2. The first clamping table 3 is movably connected with the base 1 through a first guide assembly, and the second clamping table 4 is movably connected with the base 1 through a second guide assembly so as to guide the movement of the first clamping table 3 and the movement of the second clamping table 4 respectively. Meanwhile, the first clamping table 3 is in driving connection with a first driving component on the base 1, and the second clamping table 4 is in driving connection with a second driving component on the base 1, so that the first clamping table 3 and the second clamping table 4 are driven to move through the first driving component and the second driving component respectively. The first guide assembly, the second guide assembly, the first driving assembly and the second driving assembly are all arranged along the Y direction, so that the first clamping table 3 and the second clamping table 4 can reciprocate along the X direction, and the processing station and the feeding station are switched.
It can be understood that the first clamping table 3 and the second clamping table 4 are simultaneously moved and switched, and when the first clamping table 3 (or the second clamping table 4) is at the processing station, the second clamping table 4 (or the first clamping table 3) is represented to be at the feeding station, so that the second clamping table 4 can be fed while the first clamping table 3 is processed, and efficient cleaning of the die 2 is realized.
In this embodiment, the first guiding assembly includes a first guide rail 5 and a first slider 6, where the first guide rail 5 is installed on the support plates 7 on two sides of the base 1, and the first slider 6 is installed on the lower surface of the first clamping table 3 and is slidably connected with the first guide rail 5, so that a certain distance is formed between the lower surface of the first mounting table 3 and the base 1, so that the second clamping table 4 passes through from below to switch. Correspondingly, the second guiding assembly comprises a second guide rail 8 and a second sliding block 9, the second guide rail 8 is arranged on the base 1 and positioned between the two supporting plates 7, the second sliding block 9 is arranged on the lower surface of the supporting table 10 and is in sliding connection with the second guide rail 8, and the second clamping table 4 and the supporting table 10 are connected through the lifting guiding assembly and the lifting driving assembly so as to lift.
In the present embodiment, the first drive assembly comprises a screw 11 rotatably arranged on the support plate 7, the screw 11 being in driving connection with a first motor 12. Simultaneously, first connecting block 13 is installed to first clamping platform 3, and screw hole is seted up to first connecting block 13, cooperates with lead screw 11 through the screw hole to drive lead screw 11 rotation through first motor 12, the displacement of control first clamping platform 3. Correspondingly, the second driving assembly comprises a driving pulley 14 and a driven pulley 15 rotatably arranged on the base 1, and the driving pulley 14 and the driven pulley 15 are connected through a synchronous belt 17. Meanwhile, the support table 10 is mounted with a second connection block 18, and the second connection block 18 is connected with the timing belt 17. The first clamping table 3 is further provided with a third connecting block 16, and the third connecting block 16 is connected with a synchronous belt 17 so as to transmit the power of the first motor 12 to the synchronous belt 17. The second connecting block 18 and the third connecting block 16 are respectively connected with the lower layer part and the upper layer part of the synchronous belt 17, so that when the first motor 12 works, the moving directions of the two clamping tables are opposite, and therefore, one motor is used for driving the two clamping tables to move in two directions, no time difference and no relative position difference exist, and the relative positions of the two clamping tables are still the same after repeated reciprocating movement can be ensured.
It will be appreciated that the first drive assembly, the second drive assembly, etc. may be interchangeable, or may be of other types, and are not particularly limited herein.
It should be noted that, in this embodiment, the first guide assembly, the second guide assembly, the first driving assembly, and the second driving assembly are all disposed along the Y direction, so that the first clamping table 3 and the second status table 4 all switch positions along the Y direction.
In this embodiment, the lifting guide assembly includes a linear bearing 19 disposed on the support platform and a linear guide 20 disposed on the second clamping platform 4, where the linear guide 20 is slidably matched with the linear bearing 19 to guide lifting of the second clamping platform 4 relative to the support platform 10, so as to promote stability of movement of the second clamping platform 4. The lifting driving assembly comprises a lifting air cylinder 21 arranged on the supporting table 10 in the Z direction, and a piston rod of the lifting air cylinder 21 is connected to the lower surface of the second clamping table 4 through an eccentric floating joint in a threaded manner, so that the height position of the second clamping table 4 is controlled through the expansion and contraction of an air rod.
It can be understood that, to ensure the telescopic distance of the second clamping table 4, the linear bearing 19, the lifting cylinder 21 and the like are all partially located below the supporting table 10, and since the supporting table 10 is closely disposed with the base 1, in this embodiment, the avoiding groove 22 corresponding to the linear bearing 19 and the lifting cylinder 21 is further formed on the base 1, so that the linear bearing 19 and the lifting cylinder 21 partially below the supporting table 10 can pass through and move along the avoiding groove 22 without causing obstruction.
In this embodiment, the balls 23 are uniformly distributed on the first clamping table 3 and the second clamping table 4, and the balls 23 enable the mold 2 to be conveniently moved and adjusted on the clamping tables during installation. Meanwhile, in order to ensure the stability after in-place, guide wheels 24 and locking mechanisms 25 are also arranged on the first clamping table 3 and the second clamping table 4. The guide wheel 24 is rotatably connected with the clamping table and is arranged at two adjacent sides of the positioning position of the die 2, so that the die 2 can be positioned in a welting manner. The locking mechanism 25 is arranged on the opposite side of the guide wheel 24, and can control the mold 2 to be tightly propped up, so that the mold 2 is tightly abutted against the guide wheel 24 and is tightly propped up to be limited, thereby completing the clamping and positioning of the mold 2 on the clamping table. The end of the locking mechanism 25 is provided with a buffer head of an elastic material to avoid the side surface of the die 2 from being damaged.
Also as shown in fig. 4, in this embodiment, the laser vision module includes a gantry 26 mounted above the base, and a vision recognition assembly and a laser machining assembly mounted on the gantry 26. The laser processing assembly comprises a laser input optical fiber 27, a galvanometer 28 and a field lens 29, wherein the laser input optical fiber 27 is used for inputting laser emitted by a laser, the galvanometer 28 and the field lens 29 deflect and focus laser generated by the laser, and scanning processing is carried out on corresponding positions of the die according to set scanning processing parameters. Meanwhile, the laser processing assembly further comprises a Z-axis sliding table 30, a mounting seat 31 on the Z-axis sliding table 30 is provided with a laser input optical fiber 27, a vibrating mirror 28 and a field lens 29, a distance sensor 32 is further arranged on the mounting seat 31, the distance between the surface of the die 2 and the field lens 29 is measured through the distance sensor 32, and the Z-axis sliding table 30 is controlled to ensure that the distance between the field lens 29 and the processing surface is within a preset focal length range.
The visual recognition assembly includes a visual camera 33 and a visual adjustment mechanism 34 connected to the visual camera 33, the visual adjustment mechanism 34 having Y-and Z-direction adjustment degrees of freedom, while the visual adjustment mechanism 34 is connected to the mount 31 to adjust the Y-and Z-directions of the visual camera 33 relative to the laser position. In addition, an X-axis sliding table 35 is further provided on the gantry 26, and the z-axis sliding table 30 is connected with the X-axis sliding table 35 to adjust the X-direction positions of the visual recognition component and the laser processing component so as to be aligned with the mold 2.
In the embodiment, the laser connected with the laser processing assembly can emit 50KHz/120w pulse laser, the focal depth of the laser is 12mm, surfaces with different heights can be processed, the processing precision reaches 0.005mm, the surface layer of the die to be processed can be accurately removed, and the body of the die 2 is not damaged. Of course, the parameters of the power, focal depth, frequency, etc. of the laser are variable, and other types of lasers are changed according to the processing requirements.
When the die visual identification laser cleaning device provided by the embodiment is adopted, the procedure is initialized after the die is started, the first clamping table 3 is moved to the feeding station (limited by the photoelectric sensor), the die 2 is clamped on the first clamping table 3, and initial positioning is completed.
After the first clamping table 3 finishes feeding, clicking a starting program, moving the first clamping table 3 to a processing station through a first motor 12, and simultaneously moving the second clamping table 4 to a feeding station. After moving to the preset station, the visual recognition assembly starts to recognize the machined surface (including the varying depth, irregular surface) of the mold 2 and automatically forms a scanning area in the control software, and gives the established machining parameters. Meanwhile, the distance sensor 32 of the laser processing assembly measures the distance from the field lens 29 to the processing surface of the die 2 and feeds the distance back to the industrial personal computer, and the industrial personal computer judges and controls the Z-axis sliding table 30 to move so that the field lens 29 is positioned on a proper focal length. After the adjustment, the industrial personal computer automatically controls the laser to output laser with specific parameters (the parameters of the laser can be changed according to different processing substances) to clean the surface of the die 2.
When the first clamping table 3 moves to the processing station, the air rod of the lifting air cylinder 21 below the second clamping table 4 is in a retracted state, and the height of the second clamping table 4 is lowered to a position not interfering with the first clamping table 3. When the second clamping table 4 moves to the feeding position, the air rod of the lifting air cylinder 21 automatically stretches to lift the second clamping table 4 to the same height position as the first clamping table 3. While the first clamping table 3 is being used for mold processing, the next mold 2 can be clamped on the second clamping table 4. After the die 2 on the first clamping table 3 is processed, the second clamping table 4 descends, the two clamping tables exchange positions, the second clamping table 4 ascends to a preset height, and the visual identification assembly starts to work. Thus, a working cycle is formed, and different types of dies can be processed efficiently and continuously.
Example 2:
the embodiment 2 of the invention provides a die visual identification positioning method, which specifically comprises the following steps:
s1, acquiring image information of mold placement by using a vision camera.
S2, extracting image data of the S1, extracting the edge of the die by adopting a Sobel operator, obtaining the center coordinates and the edge length of the edge of the die by adopting a Gaussian filtering algorithm, and judging the model of the die (if the die is processed before, the die can be directly processed by calling a previous configuration file in an industrial personal computer, and the die is required to be processed in a large amount in actual application, so that the step is mainly used in actual processing.
And S3, after the model is established for the mould (new mould), identifying the peripheral outline of the mould according to the image data, and transmitting the identified outline data to control software.
And S4, controlling the laser processing assembly to perform laser scanning processing according to the identified profile data.
In S2, gaussian filtering is a process of weighted averaging the whole image, and the value of each pixel is obtained by weighted averaging itself and other pixel values in the neighborhood. The specific steps of Gaussian filtering include:
s21, scanning each pixel in the image by using a template (or convolution and mask), and replacing the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template. Image gaussian smoothing is also a method for smoothing an image by using the idea of neighborhood averaging, and pixels at different positions are given different weights when the image is averaged in the image gaussian smoothing. Gaussian smoothing, unlike simple smoothing, gives pixels at different locations different weights when averaging pixels in the neighborhood, and can eliminate gaussian noise.
The specific implementation is to use a gaussian filter G (x, y) to convolve with a pixel function f (x, y) of the original mold image to obtain a smoothed I (x, y), which has the following expression:
I(x,y)＝G(x,y)*f(x,y)
s22, calculating gradient amplitude and direction of the image I (x, y) by adopting a Sobel operator, and calculating G (x) and G (y) by convolving the image I (x, y) with a Sobel horizontal operator and a Sobel vertical operator:
G(x)＝I(x,y)*Sobel x (x,y)
G(y)＝I(x,y)*Sobel y (x,y)
wherein Sobel x (x, y) is a horizontal operator, sobel y (x, y) is a vertical operator, and the values are respectively:
the amplitude M (x, y) of the image gradient is further obtained as:
the angle α (x, y) is:
s23, global threshold segmentation is carried out on the graph processed by the sobel operator, the adopted operator is threshold (Audio 2, region,0,90), specific parameters are adjusted according to different graphs, thus the curve can be segmented into a plurality of unconnected areas according to the given parameters, and after the connection (regions, connection regions) operator processing is carried out, the unconnected areas can be distinguished by different colors.
S24, screening a target straight line and acquiring data, and giving some limiting conditions, such as selecting the length of the straight line and the area of the region, and finally obtaining the target, wherein a select_shape operator is adopted in the process, and the operator select_shape selects the region according to the shape. For each input region from the region, the indicated features (features) are calculated. If each (operation= 'and') or at least one (operation= 'or') of the computational features is within the default limits (minimum, maximum), then the region will adapt to the output (copy).
In this way, the key line segments for distinguishing the dies can be obtained (different dies can be set with different identification characteristics for determining the die model.) and finally the length of the line segments can be obtained by using the condlenth operator, so that the die model can be determined.
S25, acquiring contour data of the die. Firstly, a threshold operator and a connection operator are used, some parameters are modified on the basis of S23, then a select_shape operator is used for removing some irrelevant areas, and then a start_region, a count_obj and a select_obj operator are used for obtaining oblique line segments or curved line segments on a die, so that the data value of the die contour is finally obtained. And transmitting the profile data obtained by the algorithm to control software to form a corresponding shape scanning file, and naming the corresponding shape scanning file to a specific model (when the molds of the same model are identified later, the corresponding scanning file can be directly called for processing).
Further illustrative, two straight lines shown in fig. 5 are suitable for obtaining a straight line of the die size, and the principle is that: the length of the left straight line and the length and angle of the right oblique line are different for different dies. Fig. 6-8 are results of the mold and recognition of examples.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (7)
1. The die vision recognition laser cleaning equipment is characterized by comprising a die clamping module switched by double stations and a laser vision module, wherein the die clamping module is used for clamping dies, the former die is fed to a feeding station when the former die is subjected to laser operation at a processing station, the laser vision module is used for recognizing the specific contour shape of the die to generate a corresponding scanning area, and meanwhile, the laser vision module is used for acquiring the distance between the surface of the die and the laser vision module and controlling the distance of laser processing to be in a focal depth range;
the laser vision module comprises a portal frame erected above the base, and a vision identification component and a laser processing component which are arranged on the portal frame;
the laser processing assembly comprises a laser input optical fiber, a vibrating mirror and a field lens, wherein the laser input optical fiber is used for inputting laser emitted by a laser, the vibrating mirror and the field lens deflect and focus laser generated by the laser, the laser processing assembly further comprises a Z-axis sliding table, a mounting seat on the Z-axis sliding table is provided with the laser input optical fiber, the vibrating mirror and the field lens, and a distance sensor is further arranged on the mounting seat and is used for measuring the distance between the surface of the die and the field lens;
the visual recognition component comprises a visual camera and a visual adjustment mechanism connected with the visual camera, wherein the visual adjustment mechanism is provided with a plurality of adjustment degrees of freedom, and is connected with the mounting seat so as to adjust the position of the visual camera relative to laser, and an X-axis sliding table is further arranged on the portal frame and connected with the X-axis sliding table;
a mould visual identification positioning method is adopted, which comprises the following steps:
s1, acquiring image data placed by a die by using a vision camera;
s2, extracting image data, extracting the edge of the die by adopting a Sobel operator, obtaining the center coordinates and the edge length of the edge of the die by adopting a Gaussian filtering algorithm, and judging the model of the die; s2 specifically comprises:
s21, scanning each pixel in the image by using a template, replacing the value of a central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the template, smoothing the image by Gaussian, and convolving the pixel function f (x, y) of the original mold image by using a Gaussian filter G (x, y) to obtain a smoothed I (x, y), wherein the expression is as follows:
I(x,y)＝G(x,y)*f(x,y)；
s22, calculating gradient amplitude and direction of the image I (x, y) by adopting a Sobel operator, and calculating G (x) and G (y) by convolving the image I (x, y) with a Sobel horizontal operator and a Sobel vertical operator:
G(x)＝I(x,y)*Sobel x (x,y)
G(y)＝I(x,y)*Sobel y (x,y)
wherein Sobel x (x, y) is a horizontal operator, sobel y (x, y) is a vertical operator, and the values are respectively:
the amplitude M (x, y) of the image gradient is further obtained as:
the angle α (x, y) is:
s23, global threshold segmentation is carried out on the graph processed by the sobel operator, the adopted operator is threshold, specific parameters are adjusted according to different graphs, a curve is segmented into a plurality of unconnected areas according to the given parameters, and after connection operator processing, the unconnected areas are distinguished by different colors;
s24, screening target straight lines, acquiring data, selecting given limiting conditions to obtain targets, adopting a select_shape operator in the process, selecting a region according to the shape by an operator select_shape, calculating indicated characteristics for each input region from the region, if at least one of the calculated characteristics is within a default limit, outputting the region in a fit manner, finally obtaining a key line segment for distinguishing a die, obtaining the length of the line segment by using a condutength operator, and determining the model of the die;
s25, acquiring contour data of a die; firstly, modifying parameters on the basis of S23 by using a threshold operator and a connection operator, removing some irrelevant areas by using a select_shape operator, and obtaining a diagonal segment or a curved segment on a mould by using a start_region, a count_obj and a select_obj operator to finally obtain a data value of a mould contour; transmitting the obtained profile data to software to form a corresponding shape scanning file, and naming the corresponding shape scanning file to a specific model;
s3, after the model is established for the mold, identifying the peripheral outline of the mold according to the image data, and transmitting the identified outline data to control software;
and S4, controlling the laser processing assembly to perform laser scanning processing according to the identified profile data.
2. The die visual recognition laser cleaning device according to claim 1, wherein the die clamping module comprises a base, a first clamping table and a second clamping table, wherein the first clamping table and the second clamping table are arranged on the base and are used for clamping a die, the first clamping table is movably connected with the base through a first guide assembly, the second clamping table is movably connected with the base through a second guide assembly, the first clamping table is in driving connection with a first driving assembly on the base, and the second clamping table is in driving connection with a second driving assembly on the base.
3. The die visual recognition laser cleaning device according to claim 2, wherein the first guide assembly comprises a first guide rail and a first slide block, the first guide rail is arranged on support plates on two sides of the base, and the first slide block is arranged on the lower surface of the first clamping table and is in sliding connection with the first guide rail; the second guide assembly comprises a second guide rail and a second slide block, the second guide rail is arranged on the base and positioned between the two support plates, the second slide block is arranged on the lower surface of the support table and is in sliding connection with the second guide rail, and the second clamping table is connected with the support table through the lifting guide assembly and the lifting driving assembly.
4. A die visual recognition laser cleaning device according to claim 3, wherein the first driving assembly comprises a screw rod rotatably arranged on the supporting plate, the screw rod is in transmission connection with a first motor, the first clamping table is provided with a first connecting block, and the first connecting block is provided with a threaded hole and is in threaded fit with the screw rod; the second driving assembly comprises a driving belt wheel and a driven belt wheel which are rotatably arranged on the supporting plate, the driving belt wheel is connected with the driven belt wheel through a synchronous belt, a second connecting block is arranged on the supporting table and connected with the synchronous belt, a third connecting block is further arranged on the first clamping table and connected with the synchronous belt, power of the first motor is transmitted to the synchronous belt, and the second connecting block and the third connecting block are respectively connected with a lower layer part and an upper layer part of the synchronous belt.
5. A die visual recognition laser cleaning apparatus according to claim 3, wherein said elevation guide assembly comprises a linear bearing disposed on said support table and a linear guide disposed on said second clamping table, said linear guide being in sliding engagement with said linear bearing.
6. A die visual recognition laser cleaning apparatus according to claim 3, wherein said elevation drive assembly comprises an elevation cylinder disposed on said support table, a piston rod of said elevation cylinder being connected to a lower surface of said second clamping table.
7. The die visual recognition laser cleaning device according to claim 2, wherein balls are uniformly distributed on the first clamping table and the second clamping table, and the balls are used for rolling support during die installation; the first clamping table and the second clamping table are provided with guide wheels and locking mechanisms, the guide wheels are rotatably connected with the first clamping table and the second clamping table, the guide wheels are arranged at two adjacent side edges of the die positioning position, and the locking mechanisms are arranged on one side opposite to the guide wheels and used for tightly pushing the die.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453831.5A CN115722498B (en) | 2022-11-21 | 2022-11-21 | Mold visual identification laser cleaning equipment and visual identification positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211453831.5A CN115722498B (en) | 2022-11-21 | 2022-11-21 | Mold visual identification laser cleaning equipment and visual identification positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115722498A CN115722498A (en) | 2023-03-03 |
| CN115722498B true CN115722498B (en) | 2023-08-08 |
Family
ID=85296781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211453831.5A Active CN115722498B (en) | 2022-11-21 | 2022-11-21 | Mold visual identification laser cleaning equipment and visual identification positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115722498B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116532523B (en) * | 2023-06-28 | 2023-09-19 | 广州本金机电设备有限公司 | Intelligent control longmen system of bending |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN208825873U (en) * | 2018-09-28 | 2019-05-07 | 武汉华工激光工程有限责任公司 | A kind of slide rail type Double-station bench and Double-station laser welding machine |
| CN110227688A (en) * | 2019-06-19 | 2019-09-13 | 南京集萃激光智能制造有限公司 | A kind of double-station laser cleaning equipment |
| CN113255537A (en) * | 2021-06-01 | 2021-08-13 | 贵州财经大学 | Image enhancement denoising method for identifying sailing ship |
| CN214982525U (en) * | 2021-06-03 | 2021-12-03 | 山东豪迈机械科技股份有限公司 | Automatic cleaning equipment for tire mold |
| CN215755023U (en) * | 2021-07-31 | 2022-02-08 | 苏州耐斯德自动化设备有限公司 | Double-station feeding mechanism |
| KR20220079740A (en) * | 2020-12-04 | 2022-06-14 | 파크시스템스 주식회사 | Apparatus and method for identifing probe type in atomic force microscope |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10442117B2 (en) * | 2017-04-17 | 2019-10-15 | Indian Institute Of Technology Bombay | Laser based tyre mold vent cleaning process and device |
-
2022
- 2022-11-21 CN CN202211453831.5A patent/CN115722498B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN208825873U (en) * | 2018-09-28 | 2019-05-07 | 武汉华工激光工程有限责任公司 | A kind of slide rail type Double-station bench and Double-station laser welding machine |
| CN110227688A (en) * | 2019-06-19 | 2019-09-13 | 南京集萃激光智能制造有限公司 | A kind of double-station laser cleaning equipment |
| KR20220079740A (en) * | 2020-12-04 | 2022-06-14 | 파크시스템스 주식회사 | Apparatus and method for identifing probe type in atomic force microscope |
| CN113255537A (en) * | 2021-06-01 | 2021-08-13 | 贵州财经大学 | Image enhancement denoising method for identifying sailing ship |
| CN214982525U (en) * | 2021-06-03 | 2021-12-03 | 山东豪迈机械科技股份有限公司 | Automatic cleaning equipment for tire mold |
| CN215755023U (en) * | 2021-07-31 | 2022-02-08 | 苏州耐斯德自动化设备有限公司 | Double-station feeding mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 张善文.图像模式识别.西安电子科技大学出版社,2020,76-87. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115722498A (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111530852B (en) | Laser cleaning device and laser cleaning method thereof | |
| CN109571152B (en) | Automatic workpiece polishing method based on offline programming | |
| CN115722498B (en) | Mold visual identification laser cleaning equipment and visual identification positioning method | |
| CN108296640B (en) | Laser processing apparatus and method | |
| CN106391397B (en) | A kind of determination method of glue-spraying device and frame track | |
| CN104550953B (en) | A kind of two-cylinder type desktop type selective laser melt-forming Apparatus and method for | |
| CN1150401A (en) | Control device for robot | |
| CN210306060U (en) | Automatic seek mark cutting machine | |
| CN115592272A (en) | Intelligent laser engraving device and control method thereof | |
| CN107009029B (en) | Broaching tool cutter tooth cross-scale surface pattern intelligence preparation method and device | |
| CN110899251B (en) | Laser cleaner and laser cleaning method | |
| CN207574624U (en) | A kind of fully-automatic intelligent line drawing machine | |
| CN112091439A (en) | Multi-laser-head engraving device and engraving method thereof | |
| CN1220031C (en) | Method for extracting round area from fringe pattern | |
| CN111559103A (en) | Laser cleaning device and method for tire mold | |
| CN116958178A (en) | Autonomous planning method and system for weld polishing based on laser vision | |
| CN111037919A (en) | Laser rapid prototyping machine convenient to remove | |
| CN217224926U (en) | Vibration material disk grinding device | |
| CN210024119U (en) | Infrared laser coating removing system | |
| CN205393274U (en) | Automatic blanking punching machine | |
| CN212265258U (en) | Flexible chamfering machine for disc parts based on machine vision | |
| CN210998928U (en) | Numerical control double-station prism chamfering machine | |
| CN211414693U (en) | Full-automatic multi-station polishing machine | |
| CN108161457B (en) | Automatic edge milling and deburring device and method for step machining | |
| CN106799819A (en) | A kind of method for adjusting molding parameter, device and molding machine system |
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 |