Method for determining the melt spatter frequency and for controlling a processing parameter in laser processing, as well as associated processing machine and computer program product

Abstract

Method for determining the relative frequency of molten splashes (10) when machining a workpiece (2) using a machining jet (3) wherein molten splashes (10) emerge from a melt zone (7) of the workpiece (2) melted by the machining jet (3), comprising the following method steps: - Taking several consecutive images (16) of the melting zone (7) during workpiece machining, - Generating an intensity level pixel image (17) from each captured image (16), - after processing, generating an extreme value image (18) from the recorded images (16) by determining, for each pixel in all intensity level pixel images (17), the maximum or minimum intensity value of all intensity level pixel images (17), and determining the total number (N) of those pixels in the extreme value image (18) whose maximum intensity value is greater or minimum intensity value is less than a predefined threshold (S), and - Determining the relative frequency of melt splashes (10) based on the determined total number of pixels (N).

Description

[0001] The present invention relates to a method for determining the relative frequency of melt splashes during the processing of a workpiece using a processing beam, in particular a laser beam, wherein melt splashes or particles of a coated surface emerge from a melt zone of the workpiece melted by the processing beam. The invention also relates to a processing machine suitable for carrying out this method, comprising a processing beam generator for generating a processing beam, in particular a laser beam, processing optics for directing the processing beam onto a workpiece to be processed in order to create a melt zone in the workpiece, an image recording device directed onto the melt zone, and an image processing unit for evaluating the images recorded by the image recording device.

[0002] During laser welding of almost all metallic materials, melt splashes escaping from the molten melt zone of the workpiece lead to contamination of the workpiece, which can result in costly rework and high scrap rates. Furthermore, the ejected material is missing from the weld seam, which in the worst case also requires rework. High maintenance costs also arise if the processing machine is either damaged or requires frequent cleaning. Possible causes for the occurrence of melt splashes can include: a gap or offset between two workpieces to be welded; impurities, an irregular surface; imprecise positioning of the workpieces to be welded; and incorrect parameter settings. Overall, the goal is to achieve a welding process with as little spatter as possible.

[0003] EP 3 045 255 A1 discloses a laser beam welding diagnostic method in which an image is captured of the melting zone facing away from the laser. By binarizing a predetermined area in the captured image, a grayscale image with pixel values ​​between 0 (dark) and 255 (light) is obtained. A grayscale maximum value image is then generated by determining the number of pixels in the grayscale image that have a pixel value above a predefined threshold. The pixel count thus determined correlates with the current number of melt spatter (individual events) or welding defects at the time the image was captured and allows a conclusion to be drawn as to whether a desired quality level was exceeded or not met during workpiece processing.

[0004] DE 10 2013 017 795 B3 also discloses a process monitoring system in which a grayscale image (e.g., with pixel (brightness) values ​​from 0 to 255) is generated from a captured image of the melting zone. This grayscale image is processed into a black / white binary image with a specific threshold value in order to determine the weld seam based on the black / white boundary.

[0005] US 2016 / 0 139 593 A1 and DE 11 2010 003 406 T5 show a method for ensuring and improving process quality, in which the number of pixels in each pixel image is determined whose pixel value is above or below a predetermined threshold.

[0006] In contrast, the object of the present invention is to provide a method for determining the relative frequency of melt splashes during workpiece processing and a processing machine suitable for carrying out this method.

[0007] This object is achieved according to the invention by a method for determining the relative frequency of melt splashes when machining a workpiece by means of a machining beam, wherein melt splashes emerge from a melt zone of the workpiece melted by the machining beam and wherein the method comprises the following method steps: - Recording several consecutive images of the melting zone during workpiece processing, - Generating an intensity level pixel image from each captured image, - after processing, generating an extreme value image from the recorded images by determining the maximum or minimum intensity value (brightness value) of all intensity level pixel images for each pixel in all intensity level pixel images, and determining the total number of pixels in the extreme value image whose maximum intensity value is greater or minimum intensity value is less than a predefined threshold, and - Determine the relative frequency of melt splashes based on the determined total number of pixels.

[0008] In a further aspect, the invention also relates to a method for controlling at least one processing parameter when processing a workpiece by means of a processing beam, wherein Melt splashes emerge from a melt zone of the workpiece melted by the processing beam, with the following process steps: - Recording several consecutive images of the melting zone during workpiece processing, - Generating an intensity level pixel image from each captured image, - during processing, determining the current number of pixels in each intensity level pixel image whose intensity value is greater or less than a predefined threshold, and - Controlling at least one processing parameter based on the determined current number of pixels.

[0009] Preferably, images of the melt zone are acquired during workpiece processing at a recording frequency of at least 100 Hz, in particular at least 1 kHz. The processing laser beam is a thermal processing beam, such as a laser beam or an electron beam. In the case of a laser beam, the wavelength of the laser beam must be previously blocked from the recorded light.

[0010] According to the invention, spatter is detected during workpiece processing, e.g., a welding process, using a camera. This is achieved by generating an extreme value image of all images captured during workpiece processing. The total number of pixels whose illumination changes during workpiece processing is evaluated in the extreme value image. The total number of pixels with changed illumination correlates with the relative spatter frequency. This represents only a qualitative comparison of relative spatter frequencies and not the exact number of spatters. Using the extreme value image, the processing process can be clearly differentiated into "low-spatter" and "high-spatter" processes.

[0011] According to the invention, the entire temporal sequence of workpiece processing is monitored. Full automation and online detection enable condition monitoring of the workpiece processing almost in real time. The data is generated using standard equipment under constant boundary conditions and is therefore well suited for machine learning. The greatest customer benefit is that spatter is detected from the very first moment it occurs and, by controlling one or more processing parameters, countermeasures can be taken before scrap is generated or surrounding components are contaminated or destroyed. According to the invention, spatter is detected during the welding process and eliminated through process control by actively controlling at least one processing parameter based on the determined current number of pixels. The information obtained regarding the current number of bright pixels (i.e., whether spatter is occurring or not) is used as a controlled variable.Continuous spatter monitoring is provided, allowing for control intervention. For this purpose, a control variable such as the focus position of the laser beam can be adjusted in positive and negative directions starting from a standard value. The control algorithm checks whether the current spatter frequency is increasing or decreasing and adjusts the control variable accordingly. This control can reduce scrap even during workpiece processing.

[0012] If the images only capture the thermal radiation from the process glow of the melt zone, the melt and melt splashes will appear bright in the acquired images. In this case, a maximum value image is created by generating intensity-level pixel images from the acquired images and determining the maximum intensity value of all intensity-level pixel images for each pixel in all intensity-level pixel images. Subsequently, the total number of pixels in the maximum value image whose maximum intensity value is greater than a predefined threshold is determined.

[0013] If the melt zone is additionally illuminated with an illumination source, the melt and melt splashes appear dark in the acquired images, while illuminated solid material appears bright. In this case, a minimum value image is created by generating intensity-level pixel images from the acquired images. In all intensity-level pixel images, the minimum intensity value of all intensity-level pixel images is determined for each pixel. Subsequently, the number of pixels in the minimum value image whose minimum intensity value is less than a predefined threshold is determined. An illumination laser or another light source with a red or near-infrared wavelength, such as an LED, can be used as the illumination source.

[0014] More specifically, the splashes appear dark if the lighting is set so that the background, such as a reflective photographic screen made of aluminum, copper, or light-colored plastic, is bright; in this case, the minimum value image must be evaluated. However, if the background is darkened (black background), the splashes appear bright with sufficient lighting, and the maximum value image must be evaluated.

[0015] Preferably, the total pixel count is determined only in one section of the extreme value image, and the current pixel count is determined only in one section of the intensity level pixel images. This section should be sufficiently far away from the melting zone, since its pixel values ​​are always extreme and do not contribute to the spatter frequency.

[0016] Preferably, the intensity level pixel images are generated in the form of grayscale pixel images and in all grayscale pixel images, the maximum or minimum grayscale value of all grayscale pixel images is determined for each pixel and the total number of pixels whose maximum grayscale value is greater or minimum grayscale value is less than a predefined threshold is determined.

[0017] In a preferred embodiment, if the determined total number of pixels exceeds or falls below a predetermined threshold, a warning message is issued.

[0018] Preferably, the determined total number of pixels along with the associated processing parameters are stored in a database and the stored data is evaluated.

[0019] Furthermore, the temporal change of the specific instantaneous number of pixels ("pixel change rate") in the intensity level pixel images and / or their temporal change ("pixel change acceleration") can be determined as a further measurement variable. This allows dynamic image changes due to spatter increase to be captured.

[0020] Particularly preferably, the intensity level pixel images are generated in the form of grayscale pixel images. Additionally or alternatively, the current number of pixels in each grayscale pixel image whose maximum grayscale value is greater or whose minimum grayscale value is less than a predefined threshold can be determined.

[0021] Preferably, a warning message is issued if the current pixel count exceeds or falls below a specified threshold. For example, the measured values ​​and the extreme value image can be transmitted (purely informally) to the HMI (Human Machine Interface), and warnings can be issued as soon as a machining process is affected by spatter. Using this information, the machine operator can evaluate the machining process and subsequently check the machining optics and / or machining parameters.

[0022] The total number of pixels determined according to the invention, along with the associated processing parameters, can be stored in a database in order to evaluate the stored data, in particular using artificial intelligence (AI). The evaluated data provides information about further quality characteristics or machine or optical conditions. The AI ​​controls the machining process in a closed control loop and adapts the machining parameters, such as power distribution to a double-clad fiber guiding the laser beam, focus position, power, or feed rate, to the respective machining situation. The machining machine generates no or minimal scrap and approaches the physical maximum productivity and quality through continuous improvement loops and machine learning.

[0023] In a further aspect, the invention also relates to a processing machine with a processing beam generator for generating a processing beam with processing optics for directing the processing beam onto a workpiece to be processed in order to create a melting zone in the workpiece, with an image recording device directed onto the melting zone, and with an image processing unit for evaluating the images recorded by the image recording device, wherein the image processing device comprises an intensity level pixel image generation device for generating intensity level pixel images from the recorded images and a pixel number determination device for determining the total number of those pixels in an intensity extreme value image of all intensity level pixel images whose maximum intensity value is greater or minimum intensity value is less than a predefined threshold value,and / or for determining the current number of pixels in each intensity level pixel image whose intensity value is greater or less than a predefined threshold.,

[0024] Preferably, the recording device is a camera or photodiode, which can be aligned parallel or coaxial to the processing beam impinging on the workpiece.

[0025] Further preferably, the processing machine according to the invention has a control system which controls at least one processing parameter of the processing machine on the basis of the determined instantaneous number of pixels, as well as a database in which the determined numbers of pixels together with their associated processing parameters are stored.

[0026] Finally, the invention also relates to a computer program product which has code means adapted to carry out all steps of the method according to the invention when the program runs on a control system of a processing machine.

[0027] Further advantages and advantageous embodiments of the subject matter of the invention can be found in the description, the drawings, and the claims. Likewise, the features mentioned above and those listed below can be used individually or in combination in any desired manner. The embodiments shown and described are not to be understood as an exhaustive list, but rather as examples for describing the invention.

[0028] They show: Fig. 1 schematically shows a processing machine according to the invention for laser beam welding of workpieces; Fig. 2a-2e show essential process steps of the method according to the invention for determining the frequency of melt splashes generated during laser beam welding; and Fig. 3a-3d essential process steps of the method according to the invention for controlling a processing parameter in laser beam welding.

[0029] The Fig. 1 schematically shown processing machine 1 is used to weld a workpiece 2 by means of a laser beam 3.

[0030] The processing machine 1 comprises a laser beam generator 4 for generating the laser beam 3, a processing head 5 with processing optics 6 for directing the laser beam 3 onto a workpiece 2 to be processed in order to create a molten melt zone 7 in the workpiece 2, an image recording device in the form of a camera 8 directed onto the melt zone 7, and an image processing unit 9 for evaluating the images captured by the camera 8. During laser welding of metallic workpieces 2, melt splashes 10 emerge from the melt zone 7, which negatively impact the processing result.

[0031] The laser beam 3 generated by the laser beam generator 4 strikes a dichroic mirror 11, which is reflective for the wavelength of the processing laser beam 3. The dichroic mirror 11 reflects the laser beam 3 onto the processing optics 6 by a focusing device (e.g., a focusing lens) not shown here, and from there, it is directed onto the workpiece 2. The processing optics 6 can, for example, be a laser scanner that has two mirrors, each rotatable about axes perpendicular to each other, in order to deflect the laser beam 3 two-dimensionally on the workpiece 2.

[0032] The camera 8 captures image rays 12 emanating from the melting zone 7, which are passed through the processing optics 6, the dichroic mirror 11 transparent to the image rays 12, and a further dichroic mirror 13 reflective of the image rays 12, to the camera 8, where they image the melting zone 7. As shown, the camera 8 can be aligned coaxially to the laser beam 3 using the further dichroic mirror 13. An optical filter 14 and a collimating lens 15 for focusing the image rays 12 are arranged between the further dichroic mirror 13 and the camera 8. The optical filter 14 blocks the wavelength of the laser beam 3 in order to transmit only the process light emanating from the melting zone 7, but not the laser beam 3 reflected by the workpiece 2.The camera 8 can be designed to record individual images or as a video camera to record a video sequence, wherein the recording frequency is preferably at least 100 Hz.

[0033] The detection of spatter 10 during the welding process is of particular interest if - the power distribution on a double clad fiber carrying laser beam 3 is incorrect. - the focus position of the laser beam 3 is incorrectly set or is adjusted by focus shift due to contamination of optical components. - Changes in material and batch variations may occur. - Position or device deficiencies occur.

[0034] In order to determine the relative frequency of the spatter 10 occurring during laser welding of the workpiece 2, the following procedure is used.

[0035] During workpiece processing, images 16 of the melting zone 7 are continuously recorded with the camera 8 ( Fig. 2a). Camera 8 only records the thermal radiation from the process light of the melting zone 7, so that in the recorded images 16, the melt and splashes 10 appear bright.

[0036] In a grayscale pixel image generation device 9a of the image processing device 9, grayscale pixel images 17 with pixel values ​​between 0 (dark) and 255 (light) are generated from the recorded images 16 ( Fig. 2b). In all grayscale pixel images 17, the maximum grayscale (brightness) value of all grayscale pixel images 17 is then determined for each pixel in order to generate a grayscale maximum value image 18 ( Fig. 2c).

[0037] From this maximum value image 18, the image processing device 9 defines an image section 18a in the edge area (next to the melting zone 7) ( Fig. 2d). Subsequently, in a pixel number determination device 9b of the image processing device 9, the total number N of pixels whose maximum grayscale value is greater than a predefined threshold value S is determined ( Fig. 2e). The total number N of pixels with altered illumination determined in this way correlates with the relative spatter frequency. This represents only a qualitative comparison of relative spatter frequencies and not the exact number of spatters. Using the maximum value image 18, the processing process can be clearly differentiated into "low-spatter" and "high-spatter" processes.

[0038] To reference the camera 8, a reference image is generated that corresponds to a defined, low-spatter or spatter-free state. Fig. 2e, the gray values ​​within the range with metal vapor reach values ​​of up to approximately 100, the threshold value S of the gray level value is set to 130. To calibrate the camera 8, it is therefore essential to set the threshold value S so that splashes 10 can be clearly distinguished from disturbing factors such as vapor or surface reflections.

[0039] To illuminate the melting zone 7, the processing machine 1 can have an illumination laser 19, the illumination beam 20 of which is coupled coaxially to the laser beam 3 through the two dichroic mirrors 11, 13, which are transmissive for the wavelength of the illumination beam 16 in this direction, into the processing head 5 and directed onto the melting zone 7. The illumination beam 20 reflected by the workpiece 2 travels back in the opposite direction to the further dichroic mirror 13, which is reflective in this direction and directs the illumination beam 20 onto the camera 8. In the recorded images 16, the melt and splash 10 appear dark, and the illuminated solid material appears bright. In this case, instead of the maximum value image described above, a minimum value image must be generated, the evaluation of which is carried out inversely as described above.Grayscale pixel images 17 are generated from each of the recorded images 16, and in all grayscale pixel images 17, the minimum grayscale value of all grayscale pixel images 17 is determined for each pixel to obtain the grayscale minimum value image 18. Subsequently, the total number N of pixels in the minimum value image 18 whose minimum grayscale value is smaller than a predefined threshold value S is determined. To suppress interfering reflections from the surface of the melt zone 7, a polarization filter (s-polarization) can be arranged upstream of the camera 8. Instead of the illumination laser 19, another light source with a red or near-infrared wavelength, such as an LED, can be used as the illumination source.

[0040] The images 16, the grayscale pixel images 17, and the maximum value image 18 can be forwarded by the image processing unit purely informally to the HMI (Human Machine Interface) 21: As soon as a welding process is affected by spatter, a warning message can be issued by a machine control system 22. Based on this information, the machine operator can evaluate the weld (pass / fail) and subsequently check the processing optics 6 and / or the welding parameters.

[0041] The determined total number of pixels N, along with the associated welding parameters, are stored in a database 23 and evaluated primarily using artificial intelligence (AI). The evaluated data provides information about additional quality characteristics or machine or optics conditions. The AI ​​controls the machining process in a closed control loop and adapts the machining parameters, such as power distribution to a double-clad fiber guiding the laser beam, focus position, power, or feed rate, to the respective machining situation.

[0042] The described method is controlled, for example, by the machine control 22.

[0043] Alternatively or additionally, as described in the Fig. 3a to 3d, at least one processing parameter can be controlled during processing based on the splashes 10 that occur. In Fig. 3a and Fig. 3b, analogous to the Fig. 2a and Fig. 2b, images 16 of the melting zone 7 are continuously recorded with the camera 8 and grayscale pixel images 17 are generated therefrom in the grayscale pixel image generation device 9a. From the grayscale pixel images 17, the image processing device 9 defines an identical image section 17a in the edge region (next to the melting zone 7) ( Fig. 3c). During processing, the current number Ni of pixels in each grayscale pixel image 17 whose intensity value is greater or smaller than a predefined threshold value S is determined ( Fig.3d). Depending on the instantaneous pixel number Ni thus determined, a control device 24, which may or may not be part of the machine control system 22, controls a welding parameter, such as the optical switch position for the power distribution to a double-clad fiber guiding the laser beam 3 or the focus position of the laser beam 3. The control algorithm checks whether the spatter activity is improving or decreasing and adjusts the control variables accordingly. This enables an active reduction of rejects.

Claims

[1] Method for determining the relative frequency of melt splashes (10) during machining of a workpiece (2) by means of a machining beam (3), wherein melt splashes (10) emerge from a melt zone (7) of the workpiece (2) melted by the machining beam (3), with the following method steps: - taking several chronologically successive images (16) of the melting zone (7) during workpiece machining, - generating an intensity level pixel image (17) from each recorded image (16), - after processing, generating an extreme value image (18) from the recorded images (16) by determining the maximum or minimum intensity value of all intensity level pixel images (17) for each pixel in all intensity level pixel images (17), and determining the total number (N) of those pixels in the extreme value image (18) whose maximum intensity value is greater or minimum intensity value is less than a predefined threshold value (S), and - Determining the relative frequency of the melt splashes (10) based on the determined total number of pixels (N). [2] Method according to claim 1, characterized by that the total number of pixels (N) is determined only in one image section (18a) of the extreme value image (18). [3] Method according to claim 1 or 2, characterized bythat the intensity level pixel images are generated in the form of grayscale pixel images (17) and that in all grayscale pixel images (17) for each pixel the maximum or minimum grayscale value of all grayscale pixel images (17) is determined and the total number (N) of those pixels whose maximum grayscale value is greater or minimum grayscale value is less than a predefined threshold value (S) is determined. [4] Method according to one of the preceding claims, characterized by that if the total number of pixels (N) exceeds or falls below a predetermined threshold (S), a warning message is issued. [5] Method according to one of the preceding claims, characterized by that the determined total number of pixels (N) together with the associated processing parameters is stored in a database (23) and the stored data is evaluated. [6] Method for controlling at least one processing parameter during the processing of a workpiece (2) by means of a processing beam (3), wherein melt splashes (10) emerge from a melt zone (7) of the workpiece (2) melted by the processing beam (3), comprising the following method steps: - taking several chronologically successive images (16) of the melting zone (7) during workpiece machining, - generating an intensity level pixel image (17) from each recorded image (16), - during processing, determining the current number (Ni) of those pixels in each intensity level pixel image (17) whose intensity value is greater or less than a predefined threshold value (S), and - Controlling at least one processing parameter based on the determined current number of pixels (Ni). [7] Method according to claim 6, characterized bythat the current number of pixels (Ni) is determined only in one image section (17a) of the intensity level pixel images (17). [8] Method according to claim 6 or 7, characterized by that the processing quality is additionally determined based on the temporal change of the determined instantaneous number of pixels (Ni) in the intensity level pixel images (17). [9] Method according to one of claims 6 to 8, characterized by that the processing quality is additionally determined based on the derivative of the temporal change of the determined instantaneous number of pixels (Ni) in the intensity pixel images (17). [10] Method according to one of claims 6 to 9, characterized bythat the intensity level pixel images are generated in the form of grayscale pixel images (17) and that the instantaneous number (Ni) of those pixels in each grayscale pixel image (17) whose maximum grayscale value is greater or minimum grayscale value is less than a predefined threshold value (S) is determined. [11] Method according to one of claims 6 to 10, characterized by that if the specific instantaneous number of pixels (Ni) exceeds or falls below a predetermined threshold (S), a warning message is issued. [12] Processing machine (1) with a processing beam generator (4) for generating a processing beam (3) with processing optics (6) for directing the processing beam onto a workpiece (2) to be processed in order to produce a melting zone (7) in the workpiece (2), with an image recording device (8) which is directed onto the melting zone (7), and with an image processing unit (9) for evaluating the images (16) recorded by the image recording device (8), characterized by , that the image processing device (9) comprises: - an intensity level pixel image generating device (9a) for generating intensity level pixel images (17) from the recorded images (16), and - a pixel number determination device (9b) for determining the total number (N) of those pixels in an extreme value image (18) of all intensity level pixel images (17) whose maximum intensity value is greater or minimum intensity value is less than a predefined threshold value (S), and / or for determining the current number (Ni) of those pixels in each intensity level pixel image (17) whose intensity value is greater or less than a predefined threshold value (S). [13] Processing machine according to claim 12, characterized by a control device (24) which controls at least one processing parameter of the processing machine (1) on the basis of the determined instantaneous number of pixels (Ni). [14] Processing machine according to claim 12 or 13, characterized by a database (23) in which the determined total number of pixels (N) together with their associated processing parameters are stored. [15] Processing machine according to one of claims 12 to 14, characterized by that the image recording device (8) is preceded by at least one optical filter (14) which blocks at least the wavelength of the processing beam, or a polarization filter. [16] Processing machine according to one of claims 12 to 15, characterized by a lighting source (19) directed onto the melting zone (7). [17] Computer program product comprising code means adapted to carry out all steps of the method according to one of claims 1 to 11 when the program runs on a machine control (22) of a processing machine (1).

Images