System and method for outputting identification information on a workpiece part

Abstract

The invention relates to a method for outputting identification information on a workpiece part (21) to be identified from a plurality of workpiece parts (20), the workpiece parts (20) each having a cut edge, wherein: at least one first image (6) of at least a part (25) of the cut edge of each workpiece part (20) is generated for each workpiece part (20) of the plurality of workpiece parts (20); the identification information (50) for each workpiece part (20) is assigned to the relevant first image (6); at least one second image (7) of at least a part of the cut edge of the workpiece part (21) to be identified is generated for the workpiece part (21) to be identified; the second image (7) is compared with the plurality of first images (6); the first image (6) with the greatest similarity to the second image (7) is selected, and the identification information (50) assigned to the selected first image (6) is output.

Description

[0001] System and method for outputting identification information of a workpiece part

[0002] The invention relates to a method for outputting identification information of a workpiece part.

[0003] Furthermore, the invention relates to a system for carrying out a method according to the invention.

[0004] From DE 10 2017 001 915 A1 a method for the identification of at least one component without a license plate is known.

[0005] The invention is based on the object of providing a method which further develops the state of the art.

[0006] This object is achieved by a method for outputting identification information of a workpiece part to be identified from a plurality of workpiece parts, wherein the workpiece parts each have a cutting edge, wherein for each workpiece part of the plurality of workpiece parts at least one first image of at least part of the cutting edge of the respective workpiece part is generated, wherein the identification information for the respective workpiece part is assigned to the respective first image, wherein for the workpiece part to be identified at least one second image of at least part of the cutting edge of the workpiece part to be identified is generated, wherein the second image is compared with the plurality of first images, wherein the first image with the greatest similarity to the second image is selected, wherein the identification information stored together with the selected first image is output.

[0007] In other words, in a first step, a first image of the respective cutting edge of a plurality of workpiece parts is taken. The image of the cutting edge then serves as an identification feature of the workpiece part. To identify a workpiece part from the plurality of workpiece parts, an image of the cutting edge of the workpiece part to be identified is then taken and compared with the first images. Cutting edges can be present on both outer contours and inner contours of the respective workpiece part. A cutting edge or part of a cutting edge of an outer contour is preferably used for identification.

[0008] The workpiece part to be identified is one of a multitude of workpiece parts. The method is particularly suitable for identifying individual workpiece parts from a multitude of geometrically similar or nearly similar workpiece parts.

[0009] The process enables particularly simple and reliable identification of workpiece parts with cut edges.

[0010] Preferably, the workpiece parts are sheet metal workpieces cut from sheet metal using a laser cutting machine. For workpiece parts cut from sheet metal using a laser cutting machine, the cut edge is particularly well-suited for identifying a workpiece part.

[0011] Preferably, the portion of the cutting edge for the respective first image and the second image is selected using a predetermined algorithm. By selecting a portion of the cutting edge, the data requirement is significantly reduced compared to imaging the entire cutting edge. The selection is performed algorithmically, so that the same portion of the cutting edge is reliably selected for the first image and the second image. The selection can be based on properties of the workpiece part. Particularly for workpiece parts that were cut from sheet metal using a laser cutting machine, the lead-in can be selected as the portion of the cutting edge to be imaged.

[0012] Preferably, the part of the cutting edge is selected based on the geometry of the workpiece part. By selecting based on the geometry, the same part of the cutting edge is selected for the first and second images for workpiece parts with the same geometry. Preferably, the part of the cutting edge is determined based on an enclosing rectangle of minimal area and the centroid of the workpiece part. This allows a unique part of the cutting edge to be selected very easily and reliably, especially for sheet metal workpieces.

[0013] Preferably, a property of the image is determined for each of the first images and the second image, and the properties of the second image are compared with the properties of the first images. By determining and comparing properties, the comparison of the images becomes more robust and the identification of the workpiece part more reliable. Properties of the images can, for example, be the geometric relationships of prominent points in the image. The determination of geometric relationships of prominent points in the image is known, for example, from the recognition of fingerprints or faces.

[0014] Particularly preferably, the properties are determined using a trained artificial intelligence, in particular an autoencoder. A trained autoencoder allows properties of images of the cutting edge to be encoded and compared very quickly and reliably.

[0015] Preferably, the second image and the first images are taken from a predetermined distance from the cutting edge. This predetermined distance makes geometric relationships in the images easier to compare, making the method more robust.

[0016] The invention also relates to a system for outputting identification information of a workpiece part to be identified from a plurality of workpiece parts, comprising at least one camera and a computing unit, wherein the camera is configured to generate at least one first image of at least part of the cutting edge of the respective workpiece part for a plurality of workpiece parts, wherein the camera is communicatively connected to the computing unit and is configured to transmit the first images to the computing unit, wherein the computing unit is configured to assign identification information for the respective workpiece part to the first images, wherein the camera is configured to generate at least one second image of at least part of the cutting edge of the workpiece part to be identified for a workpiece part to be identified and to transmit it to the computing unit,wherein the computing unit is configured to compare the second image with the plurality of first images, wherein the computing unit is configured to select the first image with the greatest similarity to the second image and to output the identification information associated with the selected first image via an output interface. The system is capable of recognizing a workpiece part to be identified from a plurality of first workpiece parts and outputting the associated identification information. The computing unit can be part of a machine tool for cutting out the workpiece parts. Alternatively, the computing unit can be part of a factory control system. Alternatively, the computing unit can be part of a remote computing system, e.g., a cloud. Alternatively, the computing unit can consist of several distributed computing units.wherein several of the distributed computing units are configured to carry out different steps of a method according to the invention.,

[0017] Preferably, the computing unit is configured to compare the second image with the plurality of first images by means of a predetermined algorithm.

[0018] The system preferably comprises a data storage device, wherein the computing unit is configured to store the first images and / or a respective property of the first images together with the respective associated identification information on the data storage device. By using the data storage device, the information required for identification can be retained permanently.

[0019] Preferably, the computing unit is configured to determine the respective property of the first images by means of a predetermined algorithm, in particular by means of an autoencoder.

[0020] The following description of preferred embodiments, in conjunction with the drawings, serves to explain the invention in more detail.

[0021] Shown are: Fig. 1 a process flow of a method according to the invention;

[0022] Fig. 2 is a schematic representation of a system;

[0023] Fig. 3 shows another schematic representation of a system;

[0024] Fig. 4 a selection of a part of the cutting edge; and

[0025] Fig. 5 is a perspective view of a workpiece part.

[0026] Identical or functionally equivalent elements are designated by the same reference numerals in all embodiments.

[0027] Fig. 1 shows an exemplary method sequence 100 of a method according to the invention. In a first step 110, a first image 6 is generated of each workpiece part 20 using a camera 5. In a second step 120, identification information 50 is assigned to each first image 5. In a third step 130, a second image 7 is generated of the workpiece part 21 to be identified. In a fourth step 140, the first image 6 with the greatest similarity to the second image 7 is selected. In a fifth step 150, the identification information 50 assigned to the selected first image 6 is output.

[0028] The first two steps 110, 120 are described in more detail in connection with the schematic representation of a system 1 shown in Fig. 2. The system 1 comprises a camera 5 and a computing unit 10. A plurality of workpiece parts 20 are produced by a machine tool 15, in this case a laser cutting machine. The workpiece parts 20 are geometrically almost identical and have a cutting edge on their outer contour. In the first step 110, a first image 6 of the cutting edge, or of a part of the cutting edge, is generated using the camera 5 of the system 1. The first images 6 are transmitted from the camera 5 to the computing unit 10. In the second step 120, the computing unit 10 assigns each first image 6 a piece of identification information 50. In this example, the identification information 50 is transmitted from the laser cutting machine 15 to the computing unit 10.Alternatively, the identification information 50 could be entered by an operator of the computing unit 10. For a simple and reliable comparison of the first images 6 with the second image 7, an autoencoder 55 is used by the computing unit 10 in this example. The autoencoder 55 encodes characteristic features of the cutting edge in the respective image. The computing unit 10 stores the first images 6, or the characteristic features encoded by the autoencoder, together with the respective identification information 50 in a data memory 35.

[0029] The third step 130, the fourth step 140, and the fifth step 150 are described in more detail in connection with the schematic representation of a system 1 shown in Fig. 3. In the third step, a second image 7 of the cutting edge, or of a part of the cutting edge, of the workpiece part 21 to be identified is generated using the camera 5 of the system 1. The second image 7 is transmitted from the camera 5 to the computing unit 10. In the fourth step 140, the computing unit 10 compares the second image 7 with the first images 6 and selects the first image 6 with the greatest similarity to the second image 7. In this example, for the comparison with the autoencoder 55, the characteristic features of the second image 7 are coded and compared with the coded characteristic features of the first images 6 stored in the data memory 35.In the fifth step 150, the computing unit loads the associated identification information 50 for the selected first image 6 from the data memory and outputs the identification information 50 via an output interface 30. In this example, the output interface 30 is a screen. Alternatively, the output interface 30 can be connected to a machine, in particular a machine tool, e.g., a bending machine, a deburring machine, or a marking machine. Through the direct connection, the machine can be informed how to handle the workpiece part 21 to be identified.

[0030] Fig. 4 shows a selection of a part 25 of the cutting edge. In order to avoid having to depict the entire cutting edge of the workpiece part 20 in the first image 6 or second image 7, a part 25 of the cutting edge is preferably selected. The selection of the part 25 of the cutting edge is preferably based on a geometric property of the workpiece part 30. In this example, the part 25 is selected based on an enclosing rectangle 40 with minimal area and the centroid 45 of the workpiece part 20. For the enclosing rectangle 40 with minimal area, the rectangle with the smallest area is selected from all possible enclosing rectangles. The workpiece part 20 with the enclosing rectangle 40 with minimal area is then aligned such that the centroid 45 of the workpiece part 20 lies below and to the left of the center point of the enclosing rectangle 40.From the thus aligned component, a predetermined length of the cutting edge is selected at the bottom left as part 25 of the cutting edge for the first image 6 or the second image 7. For workpiece parts 20 for which the selection of part 25 of the cutting edge is not clear using the method presented here, additional or different criteria can be used for the selection. A preferred criterion is the cutting point of the contour.

[0031] Fig. 5 shows a perspective view of the workpiece part 20 from Fig. 4. The perspective view clearly shows the thickness of the cut edge. The dashed outline shows the portion 25 of the cut edge selected for the illustration in the first image 6 and the second image 7.

[0032] List of reference symbols

[0033] 100 Procedure

[0034] 110 First Step

[0035] 120 Second step

[0036] 130 Third step

[0037] 140 Fourth step

[0038] 150 Fifth Step

[0039] 1 system

[0040] 5 Camera

[0041] 6 First picture

[0042] 7 Second picture

[0043] 10 computing unit

[0044] 15 laser cutting machines

[0045] 20 workpiece part

[0046] 25 Part of the cutting edge

[0047] 21 workpiece part to be identified

[0048] 30 Output interface

[0049] 35 data storage

[0050] 40 enclosing rectangle

[0051] 45 Center of gravity

[0052] 50 Identification information

[0053] 55 autoencoders

Claims

Patent claims 1. A method for outputting identification information (50) of a workpiece part (21) to be identified from a plurality of workpiece parts (20), wherein the workpiece parts (20) each have a cutting edge, wherein for each workpiece part (20) of the plurality of workpiece parts (20), at least one first image (6) of at least one part (25) of the cutting edge of the respective workpiece part (20) is generated, wherein the identification information (50) for the respective workpiece part (20) is assigned to the respective first image (6), wherein for the workpiece part (21) to be identified, at least one second image (7) of at least one part (25) of the cutting edge of the workpiece part (21) to be identified is generated, wherein the second image (7) is compared with the plurality of first images (6), wherein the first image (6) with the greatest similarity to the second image (7) is selected,wherein the identification information (50) associated with the selected first image (6) is output., 2. Method according to claim 1, characterized in that the workpiece parts (20, 21) are sheet metal workpiece parts cut out of a sheet metal by means of a laser cutting machine (15).

3. Method according to one of the preceding claims, characterized in that the part (25) of the cutting edge for the respective first image (6) and the second image (7) is selected by a predetermined algorithm.

4. Method according to claim 3, characterized in that the part (25) of the cutting edge is selected based on a geometric property of the workpiece part (20, 21).

5. Method according to claim 4, characterized in that the part (25) of the cutting edge is determined based on an enclosing rectangle (40) of minimal area and a center of gravity (45) of the workpiece part (20, 21).

6. Method according to one of the preceding claims, characterized in that for the first images (6) and the second image (7) a property of the image (6, 7) is determined in each case and the properties of the second image (7) are compared with the properties of the first images (6).

7. The method according to claim 6, characterized in that the properties are determined by means of a trained artificial intelligence, in particular an autoencoder (55).

8. Method according to one of the preceding claims, characterized in that the second image (7) and the first images (6) are taken from a predetermined distance from the cutting edge.

9. System (1) for outputting identification information (50) of a workpiece part (21) to be identified from a plurality of workpiece parts (20), comprising at least one camera (5) and a computing unit (10), wherein the camera (5) is configured to generate at least one first image (6) of at least one part (25) of the cutting edge of the respective workpiece part (20) for a plurality of workpiece parts (20), wherein the camera (5) is communicatively connected to the computing unit (10) and is configured to transmit the first images (6) to the computing unit (10), wherein the computing unit (10) is configured to assign identification information (50) for the respective workpiece part (20) to the first images (6), wherein the camera (5) is configured to generate at least one second image (7) of at least one part (25) of the cutting edge of the workpiece part (21) to be identified for a workpiece part (21) to be identified. generate and transmit to the computing unit (10), wherein the computing unit (10) is set up to compare the second image (7) with the plurality of first images (6), wherein the computing unit (10) is set up to select the first image (6) with the greatest similarity to the second image (7) and to output the identification information (50) assigned to the selected first image (6) via an output interface (30).

10. System according to claim 9, characterized in that the computing unit (10) is configured to compare the second image (7) with the plurality of first images (6) by means of a predetermined algorithm.

11. System according to claim 9 or 10, characterized in that the system (1) comprises a data memory (35), wherein the computing unit (10) is configured to store the first images (6) and / or a respective property of the first images (6) together with the respectively assigned identification information (50) on the data memory (35).

12. System according to one of claims 9 to 11, characterized in that the computing unit (10) is configured to determine the respective property of the first images (6) by means of a predetermined algorithm, in particular by means of an autoencoder (55).

Images