Laser welding quality evaluation system and method

Abstract

The present invention discloses a laser welding quality evaluation system and method, the evaluation system includes a laser emitting unit, a scanner for receiving the laser emitted by the laser emitting unit and generating laser rays, a scanner for scanning the welding interface of the plurality of metals, a CCD or CMOS camera for photographing the welding part; the photographed image is divided into a plurality of blocks, and a color information detection unit for detecting RGB style and brightness style from the images located in the plurality of blocks; a memory for storing RGB standard style and brightness standard style of poor welding; a laser welding machine controller for judging whether the detected RGB style and brightness style are in the plurality of RGB standard styles and plurality of brightness standard styles equivalent to poor welding stored in the memory, and judging whether the welding is good or poor. The technical solution of the present application is more comprehensive and accurate in evaluating the quality of laser welding, timely recording the number of good or poor welding, and close to practical application.

Description

Technical Field

[0001] The present invention relates to the technical field of laser welding, and in particular to a laser welding quality evaluation system and method thereof. Background Art

[0002] Patent Documents 1 and 2 describe examples of conventional laser welding quality evaluation methods.

[0003] In the laser welding quality evaluation system and method shown in patent document 1, there is disclosed an input unit that receives an image including a test sample through a 2D camera, an image processing unit that sets a focus area in the above image and converts the above focus area into a gray image, a bonding area extraction unit that detects the welding bonding area of ​​the above test sample in the above focus area, and a first detection unit that detects characteristic information of welding bonding from a two-evolution image that undergoes two-evolution processing of the above welding bonding area and the remaining background area in the above focus area, and judges whether the state of welding bonding is abnormal from the detected characteristic information, and a welding bonding recognition device using a long-range camera is disclosed, which includes a second detection unit that judges whether a welding bonding inner hole or undercut is generated from an image that combines the above two-evolution image and the above gray image, and includes a generation position.

[0004] Patent Document 2 discloses a welding quality evaluation device that evaluates the welding quality of a weld by comparing weld state data measured by an ultrasonic sensor with an evaluation standard provided by a system controller, and displays the evaluation result.

[0005] Patent Document 1: Korean Patent Publication No. 10-2018-0115646

[0006] Patent Document 2: Korean Patent No. 10-1995418 Summary of the invention

[0007] Although the above two prior patents disclose the structure of improving welding quality by using a camera, the standard RGB pattern and the standard brightness pattern of poor welding including undercut, underfill, overlay, etc. are stored in a memory, and then the RGB values ​​and brightness values ​​extracted from the video signal input from the CCD camera or the CMOS camera are compared with the RGB values ​​and brightness values ​​stored in the above memory, but the number of poor or good welding outputs is not disclosed.

[0008] The present invention aims to provide a system and method for evaluating the quality of laser welding by using an image signal input by a CCD camera or a CMOS camera during laser welding.

[0009] The technical solution of the present invention is:

[0010] The present invention provides a laser welding quality evaluation system, comprising:

[0011] Laser emitting unit, used to emit laser and weld various metals;

[0012] A scanner receives the laser emitted from the laser emitting unit and generates laser beams to scan the welding joint surface including the plurality of metals;

[0013] A CCD or CMOS camera, which photographs the welding parts according to the laser beams scanned by the scanner on the welding joint surfaces of the plurality of metals;

[0014] A color information detection unit, which divides the image captured by the CCD or CMOS camera into a plurality of blocks, and detects RGB patterns and brightness patterns from the images of the plurality of blocks;

[0015] A memory for storing RGB standard patterns and brightness standard patterns of poor welding;

[0016] The laser welding machine controller determines whether the RGB pattern and brightness pattern detected by the color information detection unit are within the RGB standard pattern and brightness standard pattern of poor welding stored in the memory, and determines whether the welding is good or poor.

[0017] Furthermore, the color information detection unit detects RGB patterns corresponding to poor welding or detects RGB patterns corresponding to good welding, and brightness patterns including undercut, underfill, overlay, and crack.

[0018] Furthermore, when the RGB pattern and brightness pattern detected by the color information detection unit are included in / fall into the RGB standard pattern and brightness standard pattern of poor welding in the memory, the memory further stores the number of poor welding in the RGB pattern and brightness pattern.

[0019] Furthermore, when the RGB pattern and brightness pattern detected by the color information detection unit are not included in the RGB standard pattern and brightness standard pattern of poor welding stored in the memory, the memory further stores the number of good welding of the RGB pattern and brightness pattern.

[0020] Furthermore, the evaluation system also includes a display device, which is used to display an RGB pattern and a brightness pattern of poor welding, and the RGB pattern and the brightness pattern of poor welding are taken from one of the RGB standard pattern and the brightness standard pattern in the memory.

[0021] The present invention also provides a laser welding quality evaluation method, which can be applied to the above-mentioned laser welding quality evaluation system. The evaluation method includes the following process:

[0022] S700: includes a stage of inputting a metal surface image captured by a CCD camera or a CMOS camera during laser welding;

[0023] S710: dividing the captured image into a plurality of blocks, and detecting an RGB pattern and a brightness pattern of the captured image through position information and color information of the plurality of captured blocks;

[0024] S720: confirming whether the style of the captured image is a standard style stored in the memory;

[0025] S730: When the pattern of the detected image is at least one standard pattern stored in the memory, a stage of adding the number of welding defects of the standard pattern stored in the memory;

[0026] S750: a stage of moving the CCD camera or the CMOS camera to a shooting position;

[0027] S760: a stage for judging whether welding is completed;

[0028] S770: When the welding is completed, the number of poor welds and the number of good welds of multiple styles are stored in the memory.

[0029] Furthermore, it also includes a stage S740, when the RGB style and brightness style of the detected image are not stored in the memory and have abnormal color and abnormal brightness, the memory further stores the number of poor welding in the RGB style and brightness style.

[0030] Furthermore, it also includes a stage S780, when the RGB style and brightness style of the detected image are not stored in the memory and have normal color and normal brightness, the memory further stores the number of good welds of the RGB style and brightness style.

[0031] Furthermore, if welding is not completed, stage S760 returns to stage S700 and the operation can be repeated.

[0032] The beneficial effects achieved by the present invention are:

[0033] During laser welding, the present invention compares the RGB standard pattern and brightness standard pattern corresponding to poor welding stored in the memory with the RGB pattern and brightness pattern of the image signal input from the CCD camera or the CMOS camera, and evaluates the welding quality based on the image signal input from the above camera to determine whether the welding is good or poor.

[0034] In addition, during laser welding, the present invention compares the RGB standard pattern and brightness standard pattern stored in the memory with the RGB pattern and brightness pattern of the image signal input by the CCD camera or the CMOS camera, and calculates the number of welding defects including undercut, underfill, overlay, crack, etc. extracted from the image signal input by the above camera, as well as the total number of welding defects, to evaluate the welding quality.

[0035] In addition, during laser welding, the present invention compares the RGB standard pattern and brightness standard pattern stored in the memory with the RGB pattern and brightness pattern of the image signal input by the CCD camera or the CMOS camera. Even if the poor welding form is not stored in the above-mentioned memory, as long as it has abnormal color or abnormal brightness, poor welding can be judged and the number of poor welding can be stored in the memory. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 11 is a schematic diagram of the structure of a laser welding quality evaluation system according to an embodiment of the present invention.

[0037] Figure 2a FIG. 1 is a schematic diagram illustrating an undercut image generated on a metal surface during welding according to an embodiment of the present invention.

[0038] Figure 2b It is a schematic diagram of an embodiment of the present invention for explaining underfill and overlay images generated on a metal surface during welding.

[0039] Figure 3a It is a schematic diagram showing an image output by a color information detection unit of underfill generated on a metal surface during welding according to an embodiment of the present invention.

[0040] Figure 3b FIG. 1 is a schematic diagram showing an underfilled RGB standard pattern image stored in a memory according to an embodiment of the present invention.

[0041] Figure 3c FIG. 1 is a schematic diagram showing an image of an underfilled brightness standard pattern stored in a memory according to an embodiment of the present invention.

[0042] Figure 4a FIG. 1 is a schematic diagram showing an image output by a color information detection unit of an undercut generated on a metal surface during welding according to an embodiment of the present invention.

[0043] Figure 4b FIG. 1 is a schematic diagram showing an RGB standard pattern of an undercut stored in a memory according to an embodiment of the present invention.

[0044] Figure 4c FIG. 1 is a schematic diagram showing a standard pattern of brightness of an undercut stored in a memory according to an embodiment of the present invention.

[0045] Figure 5a FIG. 1 is a schematic diagram showing an image output by a color information detection unit of an overlay generated on a metal surface during welding according to an embodiment of the present invention.

[0046] Figure 5b It is a drawing showing an RGB standard pattern of an overlay stored in a memory according to an embodiment of the present invention.

[0047] Figure 5c The figure is a drawing showing a standard pattern of brightness of an overlay stored in a memory according to an embodiment of the present invention.

[0048] Figure 6a This is a drawing showing an image output by a color information detection unit of a crack generated on a metal surface during welding according to an embodiment of the present invention.

[0049] Figure 6b FIG. 1 is a drawing showing an RGB standard pattern of cracks stored in a memory according to an embodiment of the present invention.

[0050] Figure 6c The figure is a drawing showing a standard pattern of brightness of cracks stored in a memory according to an embodiment of the present invention.

[0051] Figure 7 It is a flow chart showing a laser welding quality evaluation method according to an embodiment of the present invention.

[0052] In the figure, 100, laser welding quality evaluation system; 110, laser emitting unit; 120, first mirror; 130, scanner; 131, engine; 132, second mirror; 133, reflected laser path; 134, incident laser path; 140, lighting; 141, various metals; 150, third mirror; 160, CCD camera or CMOS camera; 170, color information detection unit; 180, memory; 190, laser welding machine controller; 191, display device; 210, undercut; 220, underfill; 230, overlay; 311, 411, 511, 611: RGB values ​​of normal colors; 312, RGB value of abnormal color corresponding to underfill; 313, 413, 513, 613: multiple blocks; 314, underfill pattern; 315, RGB value of normal color from underfill RGB standard pattern; 316, RGB value of abnormal color from underfill RGB standard pattern; 317, normal brightness value from underfill brightness standard pattern; 318, normal brightness value from underfill brightness standard pattern 412, abnormal brightness value obtained from the standard style; 414, undercut style; 415, normal color RGB value obtained from the underfill RGB standard style; 416, abnormal color RGB value obtained from the underfill RGB standard style; 417, normal brightness value obtained from the underfill brightness standard style; 418, underfill brightness standard style 512, RGB value of abnormal color corresponding to overlay; 514, overlay style; 515, RGB value of abnormal color obtained from underfill RGB standard style; 516, RGB value of abnormal color obtained from underfill brightness standard style; 612, RGB value of abnormal color corresponding to crack; 614, crack style; 615, RGB value of normal color obtained from underfill RGB standard style;616. RGB value of abnormal color obtained from underfill RGB standard pattern; 617. Normal brightness value obtained from underfill brightness standard pattern; 618. Abnormal brightness value obtained from underfill brightness standard pattern. ; DETAILED DESCRIPTION

[0053] To facilitate those skilled in the art to understand the present invention, specific implementations of the present invention are described below with reference to the accompanying drawings.

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0056] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component at the same time. When a component is considered to be "fixed to" another component, it may be directly fixed on the other component or there may be a central component at the same time.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0058] like Figure 1As shown, an embodiment of the laser welding quality evaluation system (100) of the present invention comprises a laser emitting unit (110) for emitting laser light for welding a plurality of metals; a scanner (130) for receiving the laser light emitted from the laser emitting unit (110) and generating laser beams to scan the welding interface portion containing the plurality of metals; a CCD or CMOS camera (160) for photographing the welding portion according to the laser beams scanned on the welding interface of the plurality of metals by the scanner (130); a color information detection unit (170) for dividing the photographed image into a plurality of blocks and detecting RGB patterns and brightness patterns from the images located in the plurality of blocks; a memory (180) for storing a plurality of RGB standard patterns and a plurality of brightness standard patterns corresponding to poor welding; and a laser welding machine controller (190) for judging whether the RGB pattern and brightness pattern detected by the color information detection unit (170) are among the plurality of RGB standard patterns and a plurality of brightness standard patterns corresponding to poor welding stored in the memory, and judging whether the welding is good or poor.

[0059] like Figure 1 As shown, an embodiment of the laser welding quality evaluation system (100) of the present invention includes a first mirror (120) for transmitting the laser light emitted by the laser emitting unit through the scanner (130).

[0060] like Figure 1 As shown, the scanner (130) includes a second mirror (132) and a motor (131) for adjusting the position of the second mirror (132).

[0061] The second mirror (132) can adjust the angle of the laser beam irradiated to the metal in the front, back, left, and right directions through the engine (131). That is, the laser beam generated by the laser emitting unit (110) is irradiated through the first mirror (120) and the second mirror (132) and irradiated along the incident laser path (134) to a position including a plurality of metal interfaces.

[0062] Then, the laser light reflected by the majority metal (141) is transmitted to the CCD camera or CMOS camera (160) along the reflected laser light path (133) through the second mirror (132) and the third mirror (150).

[0063] like Figure 1 As shown, the laser welding quality evaluation system (100) of the present invention includes an illumination (140) located between the scanner (130) and the weld metal (141) and irradiated on the metal welding surface during the welding.

[0064] One object of the present invention is to photograph the welded metal surface with a CCD camera or a CMOS camera (160) during welding, and detect poor welding conditions including at least underfill, undercut, overlay, crack, etc. from the photographed image, so as to ensure that no possible shadows will appear on the welded metal surface, thus requiring lighting (140).

[0065] like Figure 1 As shown, the color information detection unit (170) divides the image input by the CCD camera or CMOS camera (160) into a plurality of blocks.

[0066] like Figure 1 As shown, the color information detection unit (170) includes a portion for detecting corresponding RGB patterns and brightness patterns in the welding defects including underfill, undercut, overlay, and crack, and the RGB pattern and brightness pattern divide the RGB and brightness of the image taken by the camera into a plurality of blocks respectively.

[0067] like Figure 1 As shown, the memory (180) stores multiple RGB standard patterns and multiple brightness standard patterns corresponding to the poor welding including underfill, undercut, overlay and crack as standard information of the poor welding.

[0068] like Figure 1 As shown, the laser welding machine controller (190) compares the RGB value and brightness value (180) corresponding to the position information of each block input from the color information detection unit (170) with the RGB standard pattern and brightness standard pattern corresponding to at least one of the welding defects including underfill, undercut, overlay, and crack stored in the memory (180), and determines whether the comparison result corresponds to any of the welding defects including underfill, undercut, overlay, and crack corresponding to the position information of each block input from the color information detection unit (170).

[0069] like Figure 1 As shown, the laser welding quality evaluation system (100) of the present invention further includes a display device (191), which is used to display whether the image captured by the CCD or CMOS camera is poor welding or good welding. If the welding is poor, the display device (191) displays the RGB style and brightness style of the poor welding, and the RGB style and brightness style of the poor welding are taken from one of the RGB standard style and brightness standard style in the memory (180).

[0070] On the other hand, through Figure 2a and Figure 2b Examples of welding defects including underfill, undercut, and overlay are described below.

[0071] like Figure 2a As shown, undercut (210) is an example of poor welding, which means that the molten metal does not fill the groove formed along the welding line on the welding interface between the base material and the molten metal.

[0072] like Figure 2b As shown, underfill (220) and overlay (230) are also examples of poor welding. Underfill (220) refers to the state where the molten metal is not fully filled and is only below the surface height of the parent material, and overlay (230) refers to the state where the molten metal exceeds the surface height of the parent material.

[0073] like Figure 3a As shown, the output image including underfill output by the color information detection unit (170) displays normal color information, abnormal color information corresponding to underfill, multiple blocks (313) and underfill patterns (314).

[0074] like Figure 3a As shown, the normal color information may include the RGB value (311) of the normal color and position information on the plurality of blocks.

[0075] like Figure 3a As shown, the abnormal color information corresponding to the underfill may include the RGB value (312) of the abnormal color corresponding to the underfill and the position information on the plurality of blocks.

[0076] like Figure 3aAs shown, the plurality of blocks (313) are a plurality of blocks including an output image output from the color information detection unit (170) including underfill.

[0077] like Figure 3b As shown, the underfilled RGB standard pattern stored in the memory may include the RGB value (315) of the normal color obtained from the underfill and the position information of the RGB value of the normal color on the multiple blocks.

[0078] like Figure 3b As shown, the underfilled RGB standard pattern stored in the memory may include the RGB value (316) of the abnormal color obtained from the underfill and the position information of the RGB value of the abnormal color on the multiple blocks.

[0079] like Figure 3c As shown, the underfill brightness standard pattern stored in the memory may include a normal brightness value (317) obtained from underfill and position information of the normal brightness value on the multiple blocks.

[0080] like Figure 3c As shown, the underfill brightness standard pattern stored in the above-mentioned memory may include abnormal brightness values ​​(318) obtained from underfill and position information of the abnormal brightness values ​​on the above-mentioned multiple blocks.

[0081] like Figure 4a As shown, the output image including the undercut outputted from the color information detection unit (170) displays normal color information, abnormal color information corresponding to the undercut, a plurality of blocks (413) and an undercut pattern (414).

[0082] like Figure 4a As shown, the normal color information may include the RGB value (411) of the normal color and position information on the plurality of blocks.

[0083] like Figure 4aAs shown, the abnormal color information corresponding to the undercut may include the RGB value (412) of the abnormal color corresponding to the undercut and the position information on the plurality of blocks.

[0084] like Figure 4a As shown, the plurality of blocks (413) are a plurality of blocks including an output image output from the color information detection unit (170) and including an undercut.

[0085] like Figure 4b As shown, the RGB standard pattern of the undercut stored in the memory may include the RGB value (415) of the normal color obtained from the undercut and the position information of the RGB value of the normal color on the plurality of blocks.

[0086] like Figure 4b As shown, the RGB standard pattern of the undercut stored in the memory may include the RGB value (416) of the abnormal color obtained from the undercut and the position information of the RGB value of the abnormal color on the plurality of blocks.

[0087] like Figure 4c As shown, the standard brightness pattern of the undercut stored in the memory may include a normal brightness value (417) derived from the undercut and position information of the normal brightness value on the multiple blocks.

[0088] like Figure 4c As shown, the brightness standard pattern of the undercut stored in the memory may include abnormal brightness values ​​(418) derived from the undercut and position information of the abnormal brightness values ​​on the multiple blocks.

[0089] like Figure 5a As shown, it includes an overlay output image output from the above-mentioned color information detection unit (170), showing normal color information, abnormal color information corresponding to the overlay, multiple blocks (513) and an overlay style (514).

[0090] like Figure 5aAs shown, the normal color information may include the RGB value (511) of the normal color and position information on the plurality of blocks.

[0091] like Figure 5a As shown, the abnormal color information corresponding to the overlay may include the RGB value (512) of the abnormal color corresponding to the overlay and the position information on the plurality of blocks.

[0092] like Figure 5a As shown, the plurality of blocks (513) are a plurality of blocks including an output image output from the color information detection unit (170) including an overlay.

[0093] like Figure 5b As shown, the RGB standard pattern of the overlay stored in the memory may include the RGB value (515) of the abnormal color obtained from the overlay and the position information of the RGB value of the abnormal color on the multiple blocks.

[0094] like Figure 5c As shown, the brightness standard pattern of the overlay stored in the above-mentioned memory may include abnormal brightness values ​​(516) obtained from the overlay and position information of the abnormal brightness values ​​on the above-mentioned multiple blocks.

[0095] like Figure 6a As shown, the output image of the crack outputted by the color information detection unit (170) shows normal color information, abnormal color information corresponding to the crack, a plurality of blocks (613) and a standard pattern of the crack (614).

[0096] like Figure 6a As shown, the normal color information may include the RGB value (611) of the normal color and position information on the plurality of blocks.

[0097] like Figure 6a As shown, the abnormal color information corresponding to the crack may include the RGB value (612) of the abnormal color corresponding to the crack and the position information on the plurality of blocks.

[0098] like Figure 6a As shown, the plurality of blocks (613) are a plurality of blocks including an output image output from the color information detection unit (170) including an underfill.

[0099] like Figure 6b As shown, the RGB standard pattern of the crack stored in the memory may include the RGB value (615) of the normal color obtained in the crack and the position information of the RGB value of the normal color on the plurality of blocks.

[0100] like Figure 6b As shown, the RGB standard pattern of the crack stored in the memory may include the RGB value (616) of the abnormal color obtained in the crack and the position information of the RGB value of the abnormal color on the plurality of blocks.

[0101] like Figure 6c As shown, the brightness standard pattern of the crack stored in the memory may include the normal brightness value (617) appearing in the crack and the position information of the normal brightness value (617) on the multiple blocks.

[0102] like Figure 6c As shown, the brightness standard pattern of the crack stored in the memory may include the abnormal brightness value (618) appearing in the crack and the position information of the abnormal brightness value (618) on the plurality of blocks. Moreover, the user may also adjust the brightness standard pattern stored in the memory. Figures 3b to 6c The sizes of the RGB standard pattern and the brightness standard pattern are shown.

[0103] In addition, the user can also adjust the Figure 6a to Figure 6b The position of the crack in the RGB standard pattern and the brightness standard pattern.

[0104] like Figure 7 As shown, the laser welding quality evaluation method of the present invention includes the following process:

[0105] A stage of inputting a metal surface image captured by a CCD camera or a CMOS camera during laser welding (S700);

[0106] The captured image is divided into a plurality of blocks, and the RGB pattern and brightness pattern of the captured image are detected by using the position information and color information of the plurality of blocks (S710);

[0107] A step of confirming whether the pattern of the captured image is one of the standard patterns of poor welding stored in a memory (S720);

[0108] When the detected image pattern is at least one standard pattern stored in the memory, adding 1 to the number of welding defects of the standard pattern stored in the memory (S730);

[0109] Outputting the number of defective welds stored in the memory (S740);

[0110] A stage of moving the CCD camera or the CMOS camera to a shooting position (S750);

[0111] A stage of determining whether welding is completed (S760);

[0112] And when the welding is completed, the number of poor welds and the number of good welds of multiple styles are stored in the memory (S770).

[0113] As an embodiment, the step of confirming whether the pattern of the captured image is one of the standard patterns of poor welding stored in the memory (S720) includes confirming whether the pattern of the captured image is Figure 3a and even Figure 6c A stage that includes at least one of the standard patterns of poor welding.

[0114] As an embodiment, it is determined whether the style of the image captured is Figure 3a and even Figure 6c The stage of including at least one of the standard patterns of poor welding includes the stage of sequentially confirming whether the pattern of the above-mentioned captured image is at least one of the standard patterns of undercut, underfill, overlay, and crack stored in the above-mentioned memory.

[0115] As an embodiment, it is determined whether the style of the image captured is Figure 3a and even Figure 6c The step of determining at least one of the standard patterns of poor welding includes determining whether the RGB pattern of the captured image corresponds to the pattern including Figure 3b , Figure 4b , Figure 5b and Figure 6b The steps of soldering poorly at least one of the RGB standard styles.

[0116] As an embodiment, it is determined whether the style of the image captured is Figure 3a and even Figure 6cThe step of determining at least one of the standard patterns of welding defects included in the above-mentioned image includes confirming whether the brightness pattern of the above-mentioned image corresponds to the pattern included in the above-mentioned image. Figure 3b , Figure 4b , Figure 5b and Figure 6b The step of measuring at least one of the standard patterns of brightness of poor welding.

[0117] As an embodiment, it is determined whether the style of the image captured is Figure 3a and even Figure 6c The stage including at least one of the standard patterns of poor welding, when comparing the undercut standard pattern with the above-mentioned standard pattern of poor welding, may include a stage of comparing the pattern of the above-mentioned captured image with the above-mentioned undercut standard pattern and the above-mentioned undercut standard pattern with the pattern rotated 180 degrees.

[0118] As an embodiment, the pattern of the impact of the above-mentioned shooting may be composed of a plurality of standard patterns of undercut, underfill, overlay, and crack stored in the above-mentioned memory.

[0119] As an embodiment, in the laser welding quality evaluation method of the present invention, when the style of the above-mentioned captured image is combined with two or more of the standard patterns of poor welding stored in the above-mentioned memory, it also includes adding 1 to the number of poor welding in the standard patterns stored in the above-mentioned memory and outputting the stage of poor welding.

[0120] As an embodiment, the pattern of the captured image may be composed of a standard pattern of poor welding stored in the memory and a pattern of poor welding not stored in the memory.

[0121] Furthermore, the pattern of the captured image may consist of only the patterns of defective welding that are not stored in the memory.

[0122] The form of the poor welding not stored in the memory here refers to a form having an RGB value of another color or a brightness value of a different lightness in combination with the standard form of the poor welding stored in the memory.

[0123] As an embodiment, the quality evaluation method for laser welding of the present invention also includes a stage in which when the pattern of the captured image is a form of poor welding that is not stored in the memory, the number of poor welding stored in the memory is increased by 1.

[0124] As an embodiment, in the laser welding quality evaluation method of the present invention, when the style of the above-mentioned captured image does not conform to the standard style of poor welding stored in the memory and has normal color or normal brightness, the number of good welding stored in the above-mentioned memory is increased by 1 and the stage of good welding is output (S780).

[0125] As an embodiment, in the quality evaluation method of laser welding of the present invention, when the above-mentioned welding is not completed, the operation from the stage of inputting the image taken by the above-mentioned CCD camera or the above-mentioned CMOS camera to moving the shooting position of the above-mentioned CCD camera or the above-mentioned CMOS camera can be repeated, that is, stage S760 returns to stage S700, and the operation can be repeated.

[0126] The above-described embodiments of the present invention do not constitute a limitation on the protection scope of the present invention. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A laser welding quality evaluation system, characterized in that: include: Laser emitting unit, used to emit laser and weld various metals; A scanner receives the laser emitted from the laser emitting unit and generates laser beams to scan the welding joint surface including the plurality of metals; A CCD or CMOS camera, which photographs the welding parts according to the laser beams scanned by the scanner on the welding joint surfaces of the plurality of metals; A color information detection unit, which divides the image captured by the CCD or CMOS camera into a plurality of blocks, and detects RGB patterns and brightness patterns from the images of the plurality of blocks; A memory for storing RGB standard patterns and brightness standard patterns of poor welding; The laser welding machine controller determines whether the RGB pattern and the brightness pattern detected by the color information detection unit are in the RGB standard pattern and the brightness standard pattern of poor welding stored in the memory, and determines whether the welding is good or poor; When the RGB pattern and brightness pattern detected by the color information detection unit are included in the RGB standard pattern and brightness standard pattern of poor welding in the memory, the memory further stores the number of poor welding in the RGB pattern and brightness pattern; When the RGB pattern and brightness pattern detected by the color information detection unit are not included in the RGB standard pattern and brightness standard pattern of poor welding stored in the memory, the memory further stores the number of good welding of the RGB pattern and brightness pattern; The evaluation system extracts the number of welding defects such as undercut, underfill, overburden, and crack from the camera image signal, and calculates the total number of welding defects to evaluate the welding quality.

2. A laser welding quality evaluation system according to claim 1, characterized in that: The evaluation system also includes a display device, which is used to display whether the image taken by the CCD or CMOS camera is poor welding or good welding. If the welding is poor, the display device displays the RGB style and brightness style of the poor welding, and the RGB style and brightness style of the poor welding are taken from one of the RGB standard style and brightness standard style in the memory.

3. A laser welding quality evaluation method, characterized in that: Can be applied to the laser welding quality evaluation system described in any one of claims 1 to 2 above, the evaluation method The process includes: S700: includes a stage for inputting a metal surface image captured by a CCD camera or a CMOS camera during the laser welding process; S710: Divide the captured image into a plurality of blocks, and detect the RGB pattern and brightness pattern of the captured image through position information and color information of the plurality of captured blocks; S720: confirming whether the style of the captured image is a standard style stored in the memory; S730: When the pattern of the detected image is at least one standard pattern stored in the memory, a stage of adding the number of welding defects of the standard pattern stored in the memory; S740: When the RGB pattern and brightness pattern of the detected image are not stored in the memory and have abnormal color and abnormal brightness, the memory further stores the number of poor welding in the RGB pattern and brightness pattern; S750: a stage of moving the CCD camera or the CMOS camera to a shooting position; S760: a stage for judging whether welding is completed; S770: When the welding is completed, the number of poor welds and the number of good welds of multiple styles are stored in the memory; S780: When the RGB pattern and brightness pattern of the detected image are not stored in the memory and have normal color and normal brightness, the memory further stores the number of good welds of the RGB pattern and brightness pattern; The evaluation method also includes extracting the number of welding defects such as undercut, unfilled, covered, and cracked from the image signal input by the camera, and calculating the total number of welding defects to evaluate the welding quality.

4. A laser welding quality evaluation method according to claim 3, characterized in that: If welding is not completed, stage S760 returns to stage S700 and the operation can be repeated.

Images