CN101301711B - Positioning system for automatic soldering of container apex angle piece reinforcing plate - Google Patents

Abstract

The invention discloses a container vertex angle part reinforced plate automatic welding and positioning system, which is characterized in that the system comprises a camera, two lasers and a computer, wherein, an optical axis of the camera is arranged vertically to a worktable; optical planes of the dual lasers are parallel to each other and bundled together, and are installed by an angle of 45 degrees with the optical axis of the camera; the camera is connected with the computer by an image collecting card; the computer is connected with a welding robot by a data line and can control the robot to carry out corresponding operations. The container vertex angle part reinforced plate automatic welding and positioning system of the invention can realize a quick and effective initial point reinforced plate gesture recognition and positioning method by a single image processing arithmetic and simplified positioning processing type.

Description

Positioning system for automatic soldering of container apex angle piece reinforcing plate

Technical field

The present invention relates to weld container apex angle piece reinforcing plate robot welding system field, particularly the navigation system of using in this field robot welding drift angle spare process.

Background technology

At present, artificial welding is all adopted in 80% welding job in the container factory, comprises ripple weld, straight weldering, vertical position welding, overlap welding or the like.Because the coarse very difficult realization automation welding of frock realizes that fully automation increases cost again, reduces speed of production if improve frock, is the mode that present container production industry with keen competition can't be reluctant to put into practice.People-oriented, the social benefit of human-based management drives but rise day by day, requires the workman to free from abominable contaminated environment, guarantees welding quality and welding efficiency simultaneously.For addressing this problem, the Chinese container of international maximum container factory is made Qingdao branch company of Co., Ltd and is proposed demand, at different welding work posts, studies a kind of automatic welding machine people of special use.Wherein, the welding procedure of container apex angle piece reinforcing plate is simple, and plate shape, size are all known, but because production environment is coarse, tool locating is inaccurate, makes stiffener position, attitude accurately not to locate, and can not realize automatic welding; In addition, this work post requires stiffener to be welded on four angles of container, needs four workmans to finish, and causes the phenomenon that appropriation of labour power is many, welding cost is too high.Therefore, for satisfying the production actual demand, develop that a cover is with low cost, positioning accuracy is high, easy to use, and can be promoted the apex angle piece reinforcing plate used automatically the navigation system of welding become urgent need.

Summary of the invention

Task of the present invention is to provide a kind of positioning system for automatic soldering of container apex angle piece reinforcing plate, this system can realize a kind of initial point of stiffener fast and effectively location and gesture recognition method by the localization process mode of simple image processing algorithm and simplification.

Its technical solution is:

A kind of positioning system for automatic soldering of container apex angle piece reinforcing plate comprises a video camera, two laser instruments, and a computer; Wherein the vertical workbench of camera optical axis is installed, and the optical plane of twin-laser is parallel and bundle, and installs with camera optical axis angle at 45; Video camera is connected with computer by image pick-up card, and the computer expert crosses data circuit and is connected with welding robot, can control robot and carry out corresponding operating.

Above-mentioned video camera, twin-laser, blower are installed on the right angle rack; Blower is fixed on the right angle rack, and the mouth of pipe is towards workbench; Video camera is connected with computer by 1394 cards, and blower and laser instrument directly connect power supply; The computer expert crosses the RS232 agreement and communicates by letter with welding robot.

The plane of delineation of above-mentioned video camera is parallel with working face, and the plane of delineation forms corresponding proportionate relationship with working face, and obtains this ratio data by the standard rectangular template; During initial erection unit, at first by computer installation work coordinate system initial point, be initial point with the welding initial point space coordinates of template, native system is a template with first welding target, two outsides of template are respectively coordinate system x axle and y axle, and deposit its image information in ATL; In online position fixing process, two laser stripes are beaten at place, stiffener exterior angle, and video camera obtains the stiffener image that has laser labelling in real time, and obtain image information and its attitude information of initial point by Computer Processing; Obtain the initial point position, space and the attitude of real-time stiffener at last by the transformational relation of image information and spatial information.

Above-mentioned positioning system for automatic soldering of container apex angle piece reinforcing plate comprises between extraterrestrial target and its image corresponding relation corresponding relation obtain manner of cube formula, target depth information and the obtain manner of online target information really between cube formula, online target information and the reference template really;

Cube formula is as follows really for corresponding relation between above-mentioned extraterrestrial target and its image:

The plane of delineation forms corresponding proportionate relationship formula with working face:

$\left[\begin{array}{c}x\\ y\end{array}\right]=\left[\begin{array}{cc}a& b\end{array}\right]\left[\begin{array}{c}u\\ v\end{array}\right]---\left(1\right)$

Utilize the rectangle template image of a known dimensions of camera acquisition, obtaining this rectangle template from image is the length and width size of unit with the pixel, then by a=x/u, and b=y/v, the proportionality coefficient a of acquisition image space and physical space, b;

Cube formula is as follows really for corresponding relation between above-mentioned online target information and the reference template:

In the working face coordinate system, 6 points of the stiffener image of online acquisition are converted into the space coordinates point by formula (1)

Will

Be designated as θ with the axial angle of x,

Vector is designated as t, spatial point

Coordinate under coordinate system x-O-y is { (x ₁, y ₁), (x ₂, y ₂) ..., (x ₆, y ₆), can obtain by following formula:

$\left[\begin{array}{c}x\\ y\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\θ}& \sin \mathrm{\θ}\\ -\sin \mathrm{\θ}& \cos \mathrm{\θ}\end{array}\right]\left[\begin{array}{c}\tilde{x}\\ \tilde{y}\end{array}\right]+t---\left(2\right)$

Obtain (x ₁, y ₁) and (x ₂, y ₂) after, determine other each point position according to the direction and the known dimensions of stiffener;

The obtain manner of above-mentioned target depth information is as follows:

If three parallel planes, plane A are the plane of delineation, plane B and C are the space planes of differing heights, and the formed image of same object of differing heights varies in size, and concrete derivation is as follows:

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{<figure-callout\; id="1"\; label="OO"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">OO</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_1{\mathrm{<figure-callout\; id="1"\; label="b"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">b</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{c_1{\mathrm{<figure-callout\; id="1"\; label="d"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">d</figure-callout>}}_1}\left|\right|}---\left(3\right)$

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{<figure-callout\; id="1"\; label="OO"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">OO</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_2{b}_2}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{c_2{d}_2}\left|\right|}---\left(4\right)$

Wherein Be prior known depth information, With Be the length of same target, can get by formula (3) and (4):

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_2{b}_2}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{a_1{\mathrm{<figure-callout\; id="1"\; label="b"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">b</figure-callout>}}_1}\left|\right|}---\left(5\right)$

For convenience of calculation, formula (5) is converted into:

$\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|=\frac{\sqrt{S_2}}{\sqrt{{\mathrm{<figure-callout\; id="1"\; label="S"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">S</figure-callout>}}_1}}\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|---\left(6\right)$

S ₁Be the area of the medium and small rectangle of the plane of delineation, S ₂It is the area of large rectangle.Utilize this formula that target shape is generalized to arbitrary polygon, all there is this relation in attitude arbitrarily, calculates very convenient.Like this Be the depth information of reference template,

Be the online target depth information of estimating.

The obtain manner of above-mentioned online target information is as follows:

Above-mentioned laser labelling is two red laser stripeds, and the turning point that utilizes two lasing areas to form on stiffener obtains welding initial point position; Detailed process is, at first extract the R image of RGB color space, selected threshold is carried out binaryzation, denoising to it then, after thinning processing, obtain single pixel map of striation, utilize the column scan method to obtain the boundary point that striped forms at last on stiffener, fit straight line and ask its intersection point by four boundary points, promptly weld the image coordinate (u of initial point ₁, v ₁), obtain with (u by Hough transformation again ₁, v ₁) be starting point first point (u of ordering clockwise ₂, v ₂).

Positioning system for automatic soldering of container apex angle piece reinforcing plate of the present invention can be realized a kind of stiffener gesture recognition of initial point fast and effectively and localization method by the localization process mode of simple image processing algorithm and simplification.This system can determine size, the gauge of stiffener by the box parameter of system's setting, cooperates efficient algorithm to finish the work.In addition, because size, the gauge of stiffener are known, therefore, can realize automatic weld task in case determine initial point position and stiffener attitude.

Description of drawings

Fig. 1 is the principle sketch of one embodiment of the present invention, and other objects relevant with the present invention are shown simultaneously.

Fig. 2 shows a kind of corresponding relation between extraterrestrial target relevant with the present invention and the image.

Fig. 3 shows online target information relevant with the present invention and a kind of corresponding relation between the reference template.

Fig. 4 shows a kind of obtain manner of the target depth information relevant with the present invention.

Fig. 5 a～5e shows a kind of obtain manner of the online target information relevant with the present invention

The present invention will be described below in conjunction with accompanying drawing:

The specific embodiment

As shown in Figure 1, a kind of positioning system for automatic soldering of container apex angle piece reinforcing plate comprises 7, one computers 3 of 2, one blowers of 1, two laser instrument of a video camera or other suitable arithmetic units.Concrete connected mode is that video camera, twin-laser, blower are installed on the right angle rack 8, wherein requires the vertical workbench of camera optical axis to install, and the optical plane of twin-laser is parallel and bundle, and installs with camera optical axis angle at 45; Blower 7 is fixed on the right angle rack 8, and the mouth of pipe is towards workbench; Video camera is connected with computer by 1394 cards 11; Blower and laser reach and directly connect power supply; Computer 3 is communicated by letter with welding robot 4 by the RS232 agreement, can control robot and carry out corresponding operating (task).

The plane of delineation of above-mentioned video camera is parallel with working face, and the plane of delineation forms corresponding proportionate relationship with working face, and obtains this ratio data by the standard rectangular template; During initial erection unit, at first by computer installation work coordinate system initial point, be initial point with the welding initial point space coordinates of template, native system is a template with first welding target, two outsides of template are respectively coordinate system x axle and y axle, and deposit its image information in template library; In online position fixing process, two laser stripes are beaten at 10 places, exterior angle that are positioned at container roof plate 6 stiffeners 5, and video camera obtains the image of the stiffener 5 that has laser labelling in real time, and obtain image information and its attitude information of initial point 9 by Computer Processing; Obtain the initial point position, space and the attitude of real-time stiffener at last by the transformational relation of image information and spatial information.

Ginseng Fig. 2, because the vertical workbench of optical axis, promptly

Vertical space plane x-O " y and plane of delineation x-O '-y, and have following relation:

$\left[\begin{array}{c}x\\ y\end{array}\right]=\left[\begin{array}{cc}a& b\end{array}\right]\left[\begin{array}{c}u\\ v\end{array}\right]---\left(1\right)$

Utilize the rectangle template image of a known dimensions of camera acquisition, obtaining this rectangle template from image is the length and width size of unit with the pixel, then by a=x/u, and b=y/v, the proportionality coefficient a of acquisition image space and physical space, b.

Referring to Fig. 3, in the working face coordinate system, 12 is reference template, and 13 is online stiffener, and O is space coordinates initial point (0,0,0), and two external boundaries are respectively coordinate x axle and y axle, and the image information of reference template deposits ATL in advance in.6 points of the stiffener image of online acquisition are converted into the space coordinates point by formula (1) Will

Be designated as θ with the axial angle of x,

Vector is designated as t, spatial point

Coordinate under coordinate system x-O-y is { (x ₁, y ₁), (x ₂, y ₂) ..., (x ₆, y ₆), can obtain by following formula:

$\left[\begin{array}{c}x\\ y\end{array}\right]=\left[\begin{array}{cc}\cos \mathrm{\&theta;}& \sin \mathrm{\&theta;}\\ -\sin \mathrm{\&theta;}& \cos \mathrm{\&theta;}\end{array}\right]\left[\begin{array}{c}\tilde{x}\\ \tilde{y}\end{array}\right]+t---\left(2\right)$

In actual applications, our demand goes out (x ₁, y ₁) and (x ₂, y ₂), the direction of promptly welding initial point position and stiffener determines to list side by side other 4 points according to the known dimensions order.

Referring to Fig. 4, three parallel planes are arranged, plane A is the plane of delineation, plane B and C are the space planes of differing heights, and the formed image of same object of differing heights varies in size, and demonstrates among the figure, the depth information of target has relation with the area of one-tenth's image, and concrete derivation is as follows:

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{<figure-callout\; id="1"\; label="OO"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">OO</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_1{\mathrm{<figure-callout\; id="1"\; label="b"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">b</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{c_1{\mathrm{<figure-callout\; id="1"\; label="d"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">d</figure-callout>}}_1}\left|\right|}---\left(3\right)$

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{<figure-callout\; id="1"\; label="OO"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">OO</figure-callout>}}_1}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_2{b}_2}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{c_2{d}_2}\left|\right|}---\left(4\right)$

Wherein Be prior known depth information,

With

Be the length of same target, equate.Can get by formula (3) and (4):

$\frac{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|}=\frac{\left|\right|\stackrel{\&RightArrow;}{a_2{b}_2}\left|\right|}{\left|\right|\stackrel{\&RightArrow;}{a_1{\mathrm{<figure-callout\; id="1"\; label="b"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">b</figure-callout>}}_1}\left|\right|}---\left(5\right)$

For convenience of calculation, formula (5) is converted into:

$\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_3}\left|\right|=\frac{\sqrt{S_2}}{\sqrt{{\mathrm{<figure-callout\; id="1"\; label="S"\; filenames="S2008100169739E00011.png"\; state="\{\{state\}\}">S</figure-callout>}}_1}}\left|\right|\stackrel{\&RightArrow;}{{\mathrm{OO}}_2}\left|\right|---\left(6\right)$

S ₁Be the area of the medium and small rectangle of the plane of delineation, S ₂It is the area of large rectangle.Utilize this formula that target shape is generalized to arbitrary polygon, all there is this relation in attitude arbitrarily, calculates very convenient.Like this

Be the depth information of reference template, Be online detected target depth information.

Referring to Fig. 5 a～5e, in order to improve the image treatment effeciency, stamp two red laser stripeds at stiffener, the turning point that utilizes two lasing areas to form on stiffener obtains the welding initial point, as Fig. 5 a.Concrete grammar is the R image that at first extracts the RGB color space, as Fig. 5 b; Choose rational threshold value then it is carried out binaryzation, denoising,, after thinning processing, obtain single pixel map of striation, as Fig. 5 d, 5e as Fig. 5 c; Utilize the column scan method to obtain the boundary point that striped forms at last on stiffener, fit straight line and ask its intersection point, promptly weld the image coordinate (u of initial point by four boundary points ₁, v ₁), obtain with (u by Hough transformation again ₁, v ₁) be starting point first point (u of ordering clockwise ₂, v ₂), with (u ₁, v ₁) and (u ₂, v ₂) deflection be designated as the attitude of stiffener.

Column scan in this method obtains boundary point, and the prerequisite that clockwise ordering can realize is, in should using, stiffener pose excursion little (displacement＜5mm, angle＜5 °), therefore, video camera can be installed in the position that is fit to image calculation, i.e. the approximate parallel laser striped of image u axle.

The present invention carried out IMAQ before welding, so can not be subjected to the influence of arc-welding light, when welding robot commutation or pause, ventilate by blower earlier, and smog before the camera lens and dust are blown open, gathered image then.

Claims (3)

1. positioning system for automatic soldering of container apex angle piece reinforcing plate, feature is to comprise a video camera, two laser instruments, and a computer; Wherein the vertical workbench of camera optical axis is installed, and the optical plane of twin-laser is parallel and bundle, and installs with camera optical axis angle at 45; Video camera is connected with computer by image pick-up card, and the computer expert crosses data circuit and is connected with welding robot, can control robot and carry out corresponding operating.

2. positioning system for automatic soldering of container apex angle piece reinforcing plate according to claim 1 is characterized in that: described video camera, twin-laser, blower are installed on the right angle rack; Blower is fixed on the right angle rack, and the mouth of pipe is towards workbench; Video camera is connected with computer by 1394 cards, and blower and laser instrument directly connect power supply; The computer expert crosses the RS232 agreement and communicates by letter with welding robot.

3. positioning system for automatic soldering of container apex angle piece reinforcing plate according to claim 1, it is characterized in that: the plane of delineation of described video camera is parallel with working face, the plane of delineation forms corresponding proportionate relationship with working face, because the vertical workbench of optical axis, promptly

Vertical space plane x-O " y and plane of delineation x-O '-y, and have following relation:

$\left[\begin{array}{c}x\\ y\end{array}\right]=\left[\begin{array}{cc}a& b\end{array}\right]\left[\begin{array}{c}u\\ v\end{array}\right]---\left(1\right)$

Utilize the rectangle template image of a known dimensions of camera acquisition, obtaining this rectangle template from image is the length and width size of unit with the pixel, passes through a=x/u then, b=y/v, the proportionality coefficient a of the acquisition and the plane of delineation and working face ratio uniform images space and physical space, b, wherein

Be the straight line at optical axis place, x, y are space plane x-O, and " abscissa of the plane right-angle coordinate of y and ordinate, u, v are the abscissa and the ordinate of the plane right-angle coordinate of plane of delineation x-O '-y; During initial erection unit, at first by computer installation work coordinate system initial point, be initial point with the welding initial point space coordinates of template, native system is a template with first welding target, two outsides of template are respectively coordinate system x axle and y axle, and deposit its image information in ATL; In online position fixing process, two laser stripes are beaten at place, stiffener exterior angle, and video camera obtains the stiffener image that has laser labelling in real time, and obtain image information and its attitude information of the space initial point of stiffener by Computer Processing; Obtain the initial point position, space and the attitude of real-time stiffener at last by the transformational relation of image information and spatial information.

Images