Welding quality evaluation device and welding quality evaluation program

Abstract

To provide a welding quality evaluation device capable of automatically determining poor welding.SOLUTION: A welding quality evaluation device in one aspect of the present disclosure includes an imaging unit configured to acquire an image containing a weld point and surroundings of the weld point, an image processing unit configured to determine a frequency of occurrence of spatter in an image acquired by the imaging unit, and a determination unit configured to determine whether there is a welding failure or not based on the frequency of occurrence of spatter determined by the image processing unit.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a welding quality evaluation apparatus and a welding quality evaluation program.

Background Art

[0002] In the welding of metal materials, defects can occur due to various factors such as disturbances. Also, it is well known that spatter generated during welding affects the welding quality. Therefore, a method for confirming the behavior of spatter by image processing has been devised (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although the technology for recognizing spatter as described above has been devised, it is necessary to determine welding defects based on the experience of workers from the recognized spatter. Therefore, variations can occur in the criteria for determining welding defects.

[0005] One aspect of the present disclosure aims to provide a welding quality evaluation apparatus capable of automatically determining welding defects.

Means for Solving the Problems

[0006] One aspect of the present disclosure is a welding quality evaluation apparatus including an imaging unit configured to acquire an image including a welding point and the periphery of the welding point, an image processing unit configured to determine the number of occurrences of spatter in the image acquired by the imaging unit, and a determination unit configured to determine the presence or absence of welding defects based on the number of occurrences of spatter determined by the image processing unit.

[0007] It seems there are some formatting issues in the original text where some numbers in tags are not complete. I've translated it as accurately as possible while keeping those tags intact. If you can correct the original text, that would be great for a more precise translation.With this configuration, by setting the relationship between the number of spatter particles generated and welding defects, it is possible to determine whether or not there are welding defects. Therefore, automatic detection of welding defects becomes possible.

[0008] In one aspect of this disclosure, the determination unit may be configured to determine that a defect has occurred if the time during which the number of spatter generated per unit time is less than a predetermined first threshold continues for a period of time equal to or greater than a predetermined second threshold. With such a configuration, perforation can be automatically determined based on the relationship that spatter generation decreases when a hole is formed in the welded portion.

[0009] In one aspect of this disclosure, the image processing unit may be configured to count the number of sputter occurrences based on the number of pixels that have changed in the image. With such a configuration, it is possible to improve the accuracy of counting the number of sputter occurrences while suppressing the computational load.

[0010] Another aspect of this disclosure is a welding quality evaluation program that causes a computer to perform the following actions: determine the number of spatter particles in an image including the welding point and the area surrounding the welding point, and determine whether or not there are welding defects based on the determined number of spatter particles.

[0011] With this configuration, by setting the relationship between the number of spatter particles generated and welding defects, it becomes possible to automatically detect welding defects. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 is a block diagram schematically showing the configuration of the welding quality evaluation apparatus in the embodiment. [Figure 2] Figure 2 is a schematic diagram of the imaging unit in the welding quality evaluation apparatus shown in Figure 1. [Figure 3] Figure 3 is a schematic diagram showing the range of the welding image acquired by the imaging unit in Figure 2. [Figure 4] Figures 4A and 4B show an example of a single judgment frame in a welding image. [Figure 5]Figures 5A and 5B show examples of multiple judgment frames in a welding image. [Figure 6] Figure 6 shows an example of time-series data on the number of sputter events. [Figure 7] Figure 7 is a flowchart illustrating the process performed by the information processing unit of the welding quality evaluation device shown in Figure 1. [Modes for carrying out the invention]

[0013] Embodiments to which this disclosure applies will be described below with reference to the drawings. [1. First Embodiment] [1-1. Structure] The welding quality evaluation device 1 shown in Figure 1 performs welding quality evaluation (i.e., detection of defects). The welding quality evaluation device 1 comprises an imaging unit 2 and an information processing device 3.

[0014] <Photography Department> As shown in Figure 2, the imaging unit 2 is configured to acquire an image of the welded area (hereinafter also referred to as "welding image") during welding of the first workpiece W1 and the second workpiece W2 by the welding machine 101.

[0015] In this embodiment, the first workpiece W1 and the second workpiece W2 are each metal plates, and are arranged so that their ends abut each other. The welding machine 101 is a laser welding machine that joins the ends of the first workpiece W1 and the second workpiece W2 by irradiating them with a laser.

[0016] The welding machine 101 may also join the first workpiece W1 and the second workpiece W2, which are stacked in the thickness direction, in the thickness direction. Furthermore, the welding machine 101 may be other than a laser welding machine, such as an arc welding machine or a gas welding machine.

[0017] The imaging unit 2 is a camera that can continuously acquire welding images from a direction orthogonal to the plate surfaces of the first workpiece W1 and the second workpiece W2. The imaging unit 2 acquires welding images at intervals of at least 500 μs or less. The welding images include the welding point (i.e., the molten pool B) and the surroundings of the welding point.

[0018] Specifically, as shown in FIG. 3, the welding image at least includes an image of a circular determination target range A within a certain distance from the welding center P (i.e., the center of the laser beam). The radius of the determination target range A is, for example, 100 mm. A plurality of spatters S scattered from the welding point exist within the determination target range A.

[0019] <Information processing device> The information processing device 3 shown in FIG. 1 is constituted by, for example, a computer including a processor, storage media such as a RAM and a ROM, and an input / output unit. The information processing device 3 has an image processing unit 31, a determination unit 32, and a storage unit 33.

[0020] The computer constituting the information processing device 3 executes the functions as the information processing device 3 by a welding quality evaluation program stored in a storage medium (e.g., the storage unit 33). That is, the welding quality evaluation program causes the computer to determine the number of spatters generated in an image including the welding point and the surroundings of the welding point, and to determine the presence or absence of welding defects based on the determined number of spatters generated.

[0021] (Image processing unit) The image processing unit 31 is configured to determine the number of spatters generated in the welding image acquired by the imaging unit 2.

[0022] The image processing unit 31 may continuously receive the welding images from the imaging unit 2 synchronously, or may receive the welding images during that period collectively at regular reception intervals. The reception interval can be set by the user and is, for example, 15 seconds.

[0023] The image processing unit 31 counts the number of spatter occurrences based on the number of pixels that have changed within the target range of the welding image. The image processing unit 31 recognizes spatter by utilizing the fact that the areas where the light constituting the spatter exists have higher brightness than other areas in the welding image.

[0024] Specifically, the image processing unit 31 compares, pixel by pixel, the welding image that is the target of the spatter counting process (hereinafter also referred to as the "processing target image") with the welding image that occurred at the processing interval (for example, 500 μs) prior to the processing target image (hereinafter also referred to as the "comparison target image"). Here, as shown in Figure 4A, the image processing unit 31 pre-divides the processing target image into multiple judgment frames F, each consisting of, for example, 10 × 10 pixels.

[0025] The image processing unit 31 counts pixels where light is absent in the comparison image (Figure 4A) and present in the processing image (Figure 4B) as changed pixels. In Figure 4B, pixels that have changed due to sputtering S are represented by hatches.

[0026] As shown in Figure 4B, the image processing unit 31 determines that sputtering has occurred in a determination frame F if the number of changed pixels in that determination frame F is equal to or greater than a predetermined threshold (e.g., 90), and assigns a sputtering ID number (e.g., ID-1) to that determination frame F.

[0027] However, the image processing unit 31 determines that no new sputtering has occurred if, in the processing target image shown in Figure 5A, the number of changed pixels in a determination frame F1 exceeds a threshold, and it is estimated that sputtering has moved from a determination frame F2 adjacent to or near (i.e., continuous with) this determination frame F1.

[0028] Specifically, as shown in Figure 5B, if an ID number is assigned to judgment frame F2 in the comparison image (i.e., sputtering was present in judgment frame F2), it is presumed that the sputtering in judgment frame F2 moved to judgment frame F1 during the processing interval. The image processing unit 31 also transfers the ID number of judgment frame F2 of the comparison image to judgment frame F1 of the image to be processed.

[0029] Furthermore, if the image processing unit 31 determines that sputtering has occurred in multiple consecutive judgment frames, it counts the number of sputtering occurrences as 1, assuming that sputtering has occurred across these multiple judgment frames. In other words, the image processing unit 31 assigns a common ID number to the multiple judgment frames.

[0030] The image processing unit 31 determines whether sputtering has occurred in all judgment frames of the image to be processed, and calculates the total number of sputtering occurrences in the image to be processed (i.e., the number of new ID numbers to be assigned).

[0031] Furthermore, the image processing unit 31 performs this spatter generation count determination on multiple welding images acquired at each processing interval. This yields time-series data representing the change in spatter generation count at each processing interval. This time-series data is stored, for example, in the storage unit 33.

[0032] (Judgment Department) The determination unit 32 is configured to determine whether or not there are welding defects based on the number of spatter generated determined by the image processing unit.

[0033] Specifically, the determination unit 32 refers to the time-series data created by the image processing unit 31 and determines that a malfunction has occurred if the time during which the number of sputter occurrences per unit time (i.e., every 500 μs) is less than a predetermined first threshold continues for a period of time equal to or longer than a predetermined second threshold.

[0034] The first threshold is set to, for example, 12. The second threshold is set to, for example, 0.5 seconds. The first and second thresholds are set appropriately according to the welding conditions, the number of pixels in the welding image, the processing interval of the image processing unit 31, etc., using data that links the number of spatter generated and the occurrence of welding defects in welding performed in the past.

[0035] For example, if the processing interval is 500 μs, the first threshold is 12, and the second threshold is 0.5 seconds, the image processing unit 31 determines that a defect has occurred if the number of spatter occurrences is less than 12 in all 100 temporally consecutive welding images. Examples of defects determined by the determination unit 32 include welding defects due to holes.

[0036] Figure 6 shows an example of the determination process by the determination unit 32. The upper graph in Figure 6 is time-series data with time T on the horizontal axis and the number of sputter occurrences N on the vertical axis. The lower graph in Figure 6 is the output result of the determination flag, which is "1" when the number of sputter occurrences is equal to or greater than the first threshold, and "0" when it is less than the first threshold.

[0037] In period M shown in Figure 6, the judgment flag remains at "0" for a period exceeding the second threshold. Therefore, the judgment unit 32 determines that a welding defect such as a hole occurred during period M and outputs an alert.

[0038] The determination unit 32 performs welding defects in parallel with (i.e., in real time) the welding by the welding machine 101. In other words, the determination unit 32 outputs an alert to the output device as soon as a defect is detected during welding.

[0039] Furthermore, the determination unit 32 may perform quality checks after welding is completed by the welding machine 101, including determining defects after welding and outputting alerts (i.e., error logs) to the storage unit 33 and output device.

[0040] [1-2. Processing] The following describes an example of a process performed by the information processing device 3, referring to the flowchart in Figure 7.

[0041] In this process, the information processing device 3 first acquires a welding image from the imaging unit 2 (step S110). Next, the information processing device 3 counts the number of spatter (i.e., events) that occur in the acquired welding image (step S120).

[0042] After counting the number of sputter occurrences, the information processing device 3 determines whether or not a malfunction has occurred based on the number of sputter occurrences (step S130). If a malfunction has occurred (S130: YES), the information processing device 3 outputs an alert (step S140). If no malfunction has occurred (S130: NO), the information processing device 3 does not output an alert. [1-3. Effects] According to the embodiments described in detail above, the following effects can be obtained.

[0043] (1a) By setting the relationship between the number of spatter generated and welding defects, it is possible to determine whether or not there are welding defects. Therefore, automatic detection of welding defects becomes possible. (1b) By determining the occurrence of a defect when the amount of spatter generated is low for a certain period of time or longer, it is possible to automatically determine the occurrence of a hole in the welded area based on the relationship that spatter generation decreases when a hole occurs.

[0044] (1c) By counting the number of spatter generated based on the number of pixels that have changed in the welding image, it is possible to reduce the amount of computation while improving the accuracy of the spatter count.

[0045] [2. Other Embodiments] While embodiments of this disclosure have been described above, it goes without saying that this disclosure is not limited to the embodiments described above and can take various forms.

[0046] (2a) In the welding quality evaluation apparatus of the above embodiment, the procedure for counting the number of spatter generated is just one example. Therefore, the determination unit may count the number of spatter generated by a procedure other than that described above.

[0047] (2b) The welding quality evaluation apparatus of the above embodiment can also be applied to welding workpieces other than plate materials.

[0048] (2c) The functions of one component in the above embodiment may be distributed among multiple components, or the functions of multiple components may be integrated into one component. Also, some parts of the configuration of the above embodiment may be omitted. Also, at least some parts of the configuration of the above embodiment may be added to, substituted for, or otherwise replaced with the configuration of other above embodiments. Any aspect of the technical concept specified by the wording of the claims is an embodiment of the present disclosure. [Explanation of symbols]

[0049] 1...Welding quality evaluation device, 2...Imaging unit, 3...Information processing device, 31...Image processing unit, 32... Judgment unit, 33... Memory unit, 101... Welding machine.

Claims

1. An imaging unit configured to acquire an image including the welding point and the area around the welding point from the welding machine side, An image processing unit configured to determine the number of sputter occurrences in the image acquired by the imaging unit, wherein the image processing unit is configured to determine whether sputter has moved from a determination frame adjacent to or near a determination frame to a specific determination frame in which sputter is determined to be present in the image, and if it is determined that it has moved, it is not counted as a new sputter occurrence, and only if it is determined that it has not moved is it counted as a new sputter occurrence, A determination unit configured to determine whether or not there is a welding defect based on the number of spatter generated determined by the image processing unit, wherein the determination unit is configured to determine that a defect has occurred in which the molten pool in the weld is not maintained and a through hole is formed if the time for which the number of spatter generated per unit time is less than a predetermined first threshold continues for a predetermined second threshold or longer, A welding quality evaluation device equipped with the following features.

2. A welding quality evaluation apparatus according to claim 1, The welding quality evaluation apparatus is configured such that the image processing unit counts the number of spatter occurrences based on the number of pixels that have changed in the image.

3. To acquire an image from the welding machine side that includes the welding point and the area around the welding point, The process involves determining the number of spatter particles generated in an image including the welding point and its surroundings, and determining whether the spatter has moved from an adjacent or near determination frame to a specific determination frame in the image where spatter is determined to be present. If it is determined that the spatter has moved, it is not counted as a new spatter particle generation; only if it is determined that the spatter has not moved is it counted as a new spatter particle generation. Based on the determined number of spatter generated, the presence or absence of welding defects is determined, and if the time during which the number of spatter generated per unit time is less than a predetermined first threshold continues for a predetermined second threshold or longer, it is determined that a defect has occurred in which the molten pool in the weld was not maintained and a through hole was formed. A welding quality evaluation program that is executed by a computer.

Images