Method and system for determining welding state

Abstract

The method for determining the welding state comprises the steps of acquiring a first image which is an image of a welding part; measuring the intensity of light emitted from the welded member irradiated with the laser light along the moving direction of the laser light; a step for creating a second image by imaging the measured value of the intensity of the light in correspondence with the direction of movement of the laser light; and a step for determining the state of the welded portion on the basis of a determination image including the first image and the second image.

Description

Technical Field

[0001] The present disclosure relates to a welding state determination method and a welding state determination system. Background Art

[0002] In the past, in order to determine the welding state of an object subjected to laser welding, the pass / fail determination of the welding state was performed by estimating the welding strength based on the image data of the welded portion, the reflected light emitted when the laser was irradiated to the object, and the intensity of the plasma light (for example, see Patent Documents 1 and 2). In recent years, the determination of the welding state based on machine learning of artificial intelligence (AI) has also been performed (for example, see Patent Document 3). Patent Document 3 describes the determination of the welding state by AI processing based on the image data of the laser welded portion of the plate captured by a camera.

[0003] Prior Art Literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2000-061672

[0006] Patent Document 2: Japanese Patent Application Publication No. 2005-095942

[0007] Patent Document 3: Japanese Patent Application Publication No. 2020-044546 Summary of the invention

[0008] When judging the welding state of an object subjected to laser welding, the judgment is performed based on the intensity of the reflected light of the irradiated laser, the plasma light generated at the welded portion, etc. together with the image data of the welded portion, thereby improving the judgment accuracy. However, in the conventional judgment method, there is a problem that a qualified product is judged as a defective product due to a threshold value, and further improvement of the judgment accuracy is required.

[0009] The method for determining the welding state of the present disclosure determines the welding state of a welded portion formed by irradiating a welded portion with a laser beam due to relative movement of the welded portion and melting and solidifying the welded portion. The method comprises: a step of acquiring a first image as an image of the welded portion; a step of measuring the intensity of light emitted from the welded portion irradiated with the laser beam along the moving direction of the laser beam; an imaging step of creating a second image by imaging the intensity of the light corresponding to the moving direction of the laser beam; and a step of determining the state of the welded portion based on an image for determination including the first image and the second image.

[0010] The welding state determination system involved in the present disclosure determines the welding state of a welded portion formed by irradiating a welded portion with a laser beam when the laser beam moves relative to the welded portion and then melts and solidifies. The determination system comprises: an image acquisition unit that acquires a first image as an image of the welded portion; a measuring unit that measures the intensity of light emitted from the welded portion irradiated with the laser beam along the moving direction of the laser beam; an imaging processing unit that images the intensity of the light corresponding to the moving direction of the laser beam to create a second image; and a determination unit that determines the state of the welded portion based on the first image and the second image.

[0011] According to the method disclosed herein, the intensity of light emitted from the welded member irradiated with laser light is visualized and used together with the image of the welded portion to determine the welding state, thereby enabling high-precision determination. In addition, through this visualization, it is easy to use machine learning of artificial intelligence (AI) to determine the welded portion in many aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a block diagram showing a schematic configuration of a welding state determination system as an example of an embodiment.

[0013] Figure 2 This is a diagram showing an example of a welded portion.

[0014] Figure 3 This is a flowchart showing the procedure of a determination method as an example of an embodiment.

[0015] Figure 4 This is a schematic diagram for explaining a determination method as an example of an embodiment. DETAILED DESCRIPTION

[0016] Hereinafter, an example of an embodiment of a method and system for determining a welding state according to the present disclosure will be described in detail with reference to the accompanying drawings. In addition, a configuration in which a plurality of embodiments and modifications described below are selectively combined is included in the present disclosure.

[0017] In this embodiment, a battery is illustrated as a welded component. Specifically, the laser welded portion 102 of the sealing body 100 and the lead 101 of the cylindrical battery is judged to be qualified or not. However, the object of the welding state determination method and determination system involved in the present disclosure is not limited to the welding portion 102, and may also be the laser welded portion of other components constituting the battery, or the laser welded portion other than the battery. The welding state determination method and determination system involved in the present disclosure can be widely used in laser welded portions formed by moving the laser (Laser light) relative to the welded component and irradiating it.

[0018] Figure 1 1 is a block diagram showing a schematic structure of a welding state determination system 10 as an example of an embodiment. Figure 1 As shown, the determination system 10 includes a first processing unit 11, a second processing unit 12, and a third processing unit 13 as computers that execute processing for determining whether the welded portion 102 is acceptable or not. The determination system 10 further includes a camera 20 and a sensor 21. The camera 20 is an image acquisition unit that acquires an image of the welded portion 102. In this specification, the image captured by the camera 20 is referred to as a first image. The sensor 21 is a light intensity measurement unit that measures the intensity of light emitted from the welded member irradiated with the laser along the moving direction of the laser.

[0019] Although the details are described later, the determination system 10 includes: an imaging processing unit that images the measured value of the intensity of light emitted from the welded member irradiated with laser light in correspondence with the moving direction of the laser light to create a second image; and a determination unit that determines the state of the welded portion 102 based on the first image and the second image. In the determination system 10, the second processing unit 12 is the imaging processing unit, and the third processing unit 13 is the determination unit. The first processing unit 11 takes in the image captured by the camera 20 and performs a trimming process of cutting out only the portion required for the pass / fail determination of the welded portion 102.

[0020] The determination system 10 includes, for example, three computers. That is, the first processing unit 11, the second processing unit 12, and the third processing unit 13 are constituted by independent computers. Figure 1 In the example shown, the first processing unit 11 is connected to the third processing unit 13 so as to be communicable, and the second processing unit 12 is connected to the third processing unit 13 so as to be communicable. The computers constituting the determination system 10 may be connected via a local area network (LAN) or a wide area network (WAN) such as the Internet. In addition, the functions of each processing unit may be realized by one computer. Alternatively, the functions of each processing unit may be realized by four or more computers.

[0021] The computer constituting each processing unit includes: a storage unit storing programs, calculations, parameters required for processing, acquired image data, etc. for executing the functions of the processing unit; and a calculation unit reading the program to execute the pass / fail judgment of the weld and the processing required for the judgment. The calculation unit is composed of a processor such as a central processing unit (CPU). In addition, the structure of the computer constituting each processing unit is not particularly limited as long as it can execute the pass / fail judgment of the weld.

[0022] The determination system 10 is, for example, attached to a laser welding device that performs welding of the sealing body 100 and the lead wire 101. In this case, the welding state can be checked immediately after the welding process. At least a part of the structure of the determination system 10 can also be assembled in the laser welding device. In this embodiment, the light intensity measuring unit is assembled in the laser head 52 of the laser welding device. In addition, the second processing unit 12 is connected to the laser oscillator 50 so as to be communicable, and obtains the measured value of the output of the laser irradiated to the welded member from the laser oscillator 50.

[0023] The laser welding device includes a laser oscillator 50, an optical fiber 51, and a laser head 52. The laser light output from the laser oscillator 50 is transmitted to the laser head 52 via the optical fiber 51, and irradiated to the welding part from the laser head 52 arranged close to the sealing body 100 and the lead wire 101 as the welded member. A fiber laser oscillator is generally used as the laser oscillator 50, but a YAG laser oscillator or a CO laser oscillator may also be used. 2 Laser oscillator, etc.

[0024] The laser head 52 includes a reflector 53 that reflects the laser light output from the laser oscillator 50 toward the welded member and transmits the light emitted from the welded member. In addition, a focusing lens, a filter, etc. are generally provided in the laser head 52. The laser welding device includes, for example: a driving device that scans at least one of the laser head 52 or a workbench on which the welded member is placed; and a control device that controls the operation of the welding device including the laser oscillator 50, the driving device, etc.

[0025] As described above, the determination system 10 measures the intensity of light emitted from the welded member irradiated with laser light, and images the measured intensity of light. In addition, the second image obtained by the imaging is used together with the first image of the welded portion 102 captured by the camera 20 to determine the welding state. The welding state is determined by determining whether there are welding defects, which can also be done by the inspector's visual inspection, but is preferably done by computer-based image analysis, and more preferably by using an artificial intelligence (AI) model. The determination system 10 images the intensity of light emitted from the welded portion 102, and provides data suitable for AI processing to the third processing unit 13.

[0026] The determination system 10 includes a sensor 21 and a spectroscopic mechanism 22 as a light intensity measuring unit for measuring the intensity of the above-mentioned light. The light emitted from the welded member irradiated with the laser includes, for example, plasma light and thermal radiation light. In addition, it is assumed that the light emitted from the welded member irradiated with the laser includes reflected light of the laser. The determination system 10 images at least one of the plasma light, thermal radiation light and reflected light of the laser, and more preferably all of them, and uses them for determining the welding state. The determination system 10 is provided with a spectroscopic mechanism 22 for spectroscopically spectroscopically performing these lights. In Figure 1 In the illustrated example, the laser head 52 is equipped with a sensor 21 and a spectroscopic mechanism 22 .

[0027] The plasma light generated during laser welding causes absorption and refraction of the laser. Therefore, it is believed that the plasma light will reduce the energy of the laser irradiated to the welded member, for example, affecting the penetration of the weld. Therefore, defects such as insufficient penetration may occur in the welded part where the state of the plasma light changes greatly. Similarly, the thermal radiation light (near infrared light) generated from the weld and the reflected light of the laser reflected from the weld are useful for determining the welding state, and large changes in the thermal radiation light and the reflected light enable defects in the weld to be estimated.

[0028] exist Figure 1 In the figure, one sensor 21 is shown, but the sensor 21 includes a first sensor that receives plasma light and measures its intensity, a second sensor that receives thermal radiation light and measures its intensity, and a third sensor that receives reflected light of laser and measures its intensity. The sensor 21 is, for example, a photodiode having a sensitive region in the wavelength region of the detection target light, and outputs an electrical signal corresponding to the intensity of the light as detection information. In addition, as the light intensity measuring unit, a device in which a spectroscopic mechanism and a sensor capable of detecting reflected light of each wavelength are integrated can also be used.

[0029] In the determination system 10, the detection information of the sensor 21 is sent to the second processing unit 12, and the image processing of the measured values ​​of the intensity of the plasma light, the thermal radiation light, and the reflected light is performed in the second processing unit 12. The second processing unit 12 further obtains the measured value of the output of the laser from the laser oscillator 50 and performs the image processing of the measured value.

[0030] Figure 2 1 is a diagram showing a welding portion 102 between a sealing body 100 and a lead 101. Figure 1 as well as Figure 2As shown, the welding portion 102 is formed by irradiating the surface of the lead 101 with a laser while the lead 101 is overlapped on the sealing body 100. The lead 101 is, for example, a strip-shaped conductive member connected to the positive electrode, and is composed of a metal with aluminum as the main component. The thickness and width of the lead 101 can be appropriately changed according to the size of the battery, etc. As an example, the thickness is greater than 50μm and less than 500μm, and the width is greater than 2mm and less than 10mm. The sealing body 100 is thicker than the lead 101 and includes a metal plate to which the lead 101 is welded. The metal plate is, for example, composed of a metal with aluminum as the main component.

[0031] exist Figure 2 In the example shown, the welding portion 102 extends parallel to the width direction of the lead 101 and is formed into a thin line having a substantially constant width. The width of the welding portion 102 is, for example, 1 mm or more and 4 mm or 1.5 mm or more and 3.5 mm or less. The laser is irradiated to the welded member while being relatively moved relative to the welded member, and the irradiated portion of the laser is melted and solidified, thereby forming the welding portion 102. The relative movement of the laser relative to the welded member is performed by scanning at least one of the laser and the worktable on which the welded member is placed.

[0032] Below, refer to Figure 3 as well as Figure 4 The method for determining the welding state is described in detail. Figure 3 This is a flowchart showing the procedure of the determination method according to the present embodiment.

[0033] like Figure 3 As shown, the determination method of this embodiment includes the following steps.

[0034] (1) An image acquisition step of acquiring a first image of the welded portion 102 ( S10 ).

[0035] (2) A light intensity measuring step ( S11 ) of measuring the intensity of light emitted from the members to be welded (sealing body 100 and lead wire 101 ) irradiated with the laser light along the moving direction of the laser light to acquire measurement data.

[0036] (3) An imaging processing step of imaging the measured light intensity and the moving direction of the laser light to create a second image ( S14 ).

[0037] (4) A determination step of determining the state of the welded portion 102 based on the determination image including the first image and the second image ( S16 ).

[0038] The determination method of this embodiment further includes a step of combining the first image and the second image to create a combined image (S15). In addition, the combined image is used as the determination image in the above determination step. The determination step preferably determines the state of the weld 102 based on the learning data obtained by machine learning of the determination image. By imaging the measured value of the intensity of the light emitted from the weld 102 and providing it to the third processing unit 13 as a combined image, the accuracy of machine learning is improved, and the determination accuracy of the welding state is further improved. The combined image is one data combining multiple images.

[0039] The determination method of this embodiment further includes a step (S13) of normalizing the intensity of the measured light to create parameters for imaging. In this case, in the imaging processing step of S14, the second image is created using the parameters. Regarding the measured values ​​of plasma light, thermal radiation light, and reflected light, since their scales are sometimes greatly different, it is assumed that when the original values ​​are used for imaging, the accuracy of machine learning is reduced or learning takes time. Therefore, for example, it is preferable to perform standardization to make the scale of the measurement data consistent.

[0040] The determination method of this embodiment also includes a step (S12) of measuring the output of the laser irradiated to the welded member along the moving direction of the laser. The laser oscillator 50, for example, measures the output of the emitted laser. Alternatively, a laser power meter may be provided on the laser head 52 or the like. The measured value of the laser output is standardized in the same manner as the measured value of the plasma light, etc., and is imaged corresponding to the moving direction of the laser. In step S14, a third image based on the measured value of the laser output is created together with the second image. In this case, the third image is included in the determination image together with the first image and the second image.

[0041] Figure 4 Schematic diagram showing the determination method of this embodiment. Figure 4 As shown, in the determination method of this embodiment, an image (original image) of a welded member including a welded portion 102 is captured, and the intensity of light emitted from the welded portion 102 is measured to obtain measurement data. The original image is captured by the camera 20, for example, after the welding process is completed, and its image data is sent to the first processing unit 11. In addition, the image of the welded portion 102 can also be acquired in real time during the welding process. The first processing unit 11 performs a trimming process to cut off unnecessary parts from the original image and retain only the image of the welded portion 102, thereby creating a first image 31 of the welded portion 102.

[0042] The measurement data is acquired in real time during the welding process, for example. The acquired measurement data is imaged after being standardized. As described above, the measurement data imaged in the imaging process step includes the measured values ​​of the intensity of plasma light, thermal radiation light, and reflected light of the laser obtained by spectroscopically splitting the light emitted from the welded member irradiated with the laser. The intensity of each light is measured in real time during welding by the sensor 21 and the spectroscopic mechanism 22 along the moving direction of the laser, that is, along the length direction of the weld 102. The measurement data further includes the measured value of the output of the laser measured in real time along the moving direction of the laser.

[0043] The outline of the normalization process and the imaging process of each measurement data is as follows.

[0044] (1) For the measurement values ​​constituting the measurement data, the maximum value and the minimum value are extracted.

[0045] (2) For the measured values, a conversion formula is calculated such that the maximum value is 255 (depth value: white) and the minimum value is 0 (depth value: black).

[0046] (3) According to the above conversion formula, each measured value is replaced by a numerical value in the range of 0 to 255. The numerical value in the range of 0 to 255 is Figure 3 Parameters for imaging in step S13.

[0047] (4) The measurement data is converted into an image by repeatedly assigning a color depth to the replaced numerical value (a numerical value in the range of 0 to 255) according to the magnitude of the numerical value and arranging them as one pixel. In other words, the measurement data consisting of the measurement value of the light intensity and the measurement value of the laser output are converted into image data.

[0048] By executing the above-mentioned processing (1) to (4) on all the measurement data, a second image 33 based on the measurement value of plasma light, a second image 34 based on the measurement value of thermal radiation light, a second image 35 based on the measurement value of laser reflected light, and a third image 36 based on the measurement value of laser output are created. Then, the first image 31, the second images 33, 34, 35, and the third image 36 of the welded portion 102 captured by the camera 20 are combined to create a combined image 37 as a single judgment image. In addition, when creating an image as data of a large range, it is preferable to perform a pooling process to compress the number of pixels.

[0049] The normalization processing and image processing of the measurement data are performed in the second processing unit 12. The second processing unit 12 obtains the measurement values ​​of each light intensity for the measurement points set along the moving direction of the laser, for example. That is, the measurement values ​​of each light intensity are obtained at the same measurement points. The number of measurement points is not particularly limited, and several thousand to tens of thousands of points may be set in a row along the moving direction of the laser. Similarly, the measurement value of the output of the laser is measured at the same point as the measurement point of each light intensity.

[0050] In the determination method of the present embodiment, the combined image 37 is sent to the third processing unit 13 to determine whether the welding state is qualified or not. This determination step is preferably performed based on the learning data obtained by machine learning of the combined image 37. The third processing unit 13, for example, uses an AI model for images to determine whether the welding portion 102 is qualified or not based on the acquired combined image 37. That is, the combined image 37 is given as an input value of the AI ​​model. In addition, for the AI ​​model, commercially available software for images can be used, and the previous AI model can be used as it is. That is, according to the determination method of the present embodiment, by imaging various data of different scales and dimensions, abnormality detection under a wide viewpoint, which AI excels in, becomes easy.

[0051] like Figure 4 As shown, the combined image 37 is arranged so that the first image 31, the second images 33, 34, 35 and the third image 36 do not overlap each other and constitute one data. As described above, each image is composed of a plurality of pixels 38 arranged in a row along the moving direction of the laser, and has a length direction and a width direction. Figure 4 Although the combined image 37 is schematically shown, the second images 33, 34, 35 and the third image 36 have, for example, several thousand to several tens of thousands of pixels 38 corresponding to the measurement points in the longitudinal direction of each image. On the other hand, the width direction is composed of one pixel 38.

[0052] The combined image 37 is configured such that the width direction of each image is oriented toward the direction X in which each image is arranged. In addition, pixels 38 (parameters for imaging) based on numerical data corresponding to the same measurement point of each image are arranged along the direction X. Figure 4 In the example shown, the plurality of images constituting the combined image 37 are arranged in the order of the first image 31 captured by the camera 20, the third image 36 of the measured value of the laser output, the second image 35 of the laser reflected light, the second image 33 of the plasma light, and the second image 34 of the thermal radiation light, but the order of the images is not limited to this as long as the AI ​​model can recognize it as one data. In addition, the combined image 37 can also be constructed by overlapping the image data.

[0053] As described above, the pass / fail judgment of the weld 102 using the combined image 37 is preferably implemented based on the learning data obtained by machine learning of AI. Machine learning can apply a conventionally known method, and the method is not particularly limited. In addition, deep learning is included in machine learning. For example, the pattern of qualified and unqualified products of the weld 102 is input to the third processing unit. In addition, by performing machine learning through AI, it is possible to perform a pass / fail judgment of the welding state based on AI. In the judgment step, the combined image 37 as one data is input to the AI ​​model, and the presence or absence of abnormal parts is determined based on the learning data.

[0054] The AI ​​model sets parameters for machine learning, such as the image size and number of convolution processing, the selection of convolution processing filters, the selection of activation processing filters, the selection of sparse processing filters, the size and number of sparse processing, the size and number of intermediate layers of perceptron combination processing, the filtering ratio, the number of epochs, etc. And, based on the learning data and the combined image 37 as the result of machine learning, the welding state is determined in real time.

[0055] The AI ​​model reads the image data for learning, performs machine learning based on the pre-set initial parameters at the beginning, and then performs machine learning based on the parameters calculated by learning. For example, the coefficients, thresholds, offset values, etc. for weighting the values ​​of each pixel 38 of the image are changed, and the weighting coefficient with the highest probability of conforming to the welding state is finally determined. In the case of deep learning, it can include locally weighted layers or globally weighted layers.

[0056] The AI ​​model determines the degree of consistency with various welding conditions by comparing the learning data with the combined image 37, for example. The consistency determination results of each degree of consistency are weighted or evaluated using a threshold value, thereby comprehensively determining the degree of consistency with various welding conditions and determining the welding condition with the highest degree of consistency.

[0057] The following effects are listed as the effects of the determination method of this embodiment.

[0058] (1) By converting each numerical data into an image, it is not necessary to use a complicated AI model corresponding to each data, and it is possible to use an AI model corresponding only to the image data.

[0059] (2) Multiple numerical data can be uniformly visually recognized as depth values ​​(black, gray, and white) on an image, and by comparing them with surrounding values ​​on the image, it is possible to focus only on the amount of change in each data.

[0060] (3) By performing the pooling process on the image data, it is possible to perform analysis in which the range of the analysis data is narrowed down from a larger range such as monthly units, daily units, hourly units, etc.

[0061] (4) By visualizing numerical data, since the data has a two-dimensional positional relationship, analysis focusing on the information contained in the positional relationship can be performed.

[0062] (5) As a processing method for image data, not only AI models have been developed, but also various image processing methods have been developed, and analysis can also be performed using these methods. Depending on the analysis method, it is possible to focus only on slow changes, only on rapid changes, or to remove noise data, etc.

[0063] (6) Since image data is easy for humans to visually recognize, data over a wide range can be checked at a glance.

[0064] As described above, according to the determination method of this embodiment, numerical data such as the intensity of light emitted from the welded member irradiated with laser light is visualized and used together with the image of the welded portion for determining the welding state, thereby enabling high-precision pass / fail determination. In addition, through this visualization, the application of various analytical methods including AI models becomes easy. When using the AI ​​model for pass / fail determination, it is easy to determine the welding state in many aspects.

[0065] In addition, rapid temperature changes and changes in the state of the material will occur in the laser welding part, and it is not easy to analyze the welding state. Therefore, the optimization of parameters related to laser welding is established in terms of the accumulation of trial and error. In addition, during mass production, sputtering, perforation and other poor welding may occur due to various complex factors. Therefore, in the determination method of this embodiment, various wide-range data are obtained as input values ​​of the determination step. On the other hand, the problem of using various data as input values ​​is that the data format and scale are different, but by imaging these numerical data and inputting them into the AI ​​model as image data, the pass or fail judgment of the welding state can be performed in many aspects and with high precision.

[0066] The present disclosure is further illustrated by the following embodiments.

[0067] Configuration 1: A method for determining a welding state, for determining a welding portion formed by irradiating a member to be welded with a laser beam when the member to be welded moves relative to the member to be welded and melts and solidifies, the method comprising: a step of acquiring a first image as an image of the welding portion; a step of measuring the intensity of light emitted from the member to be welded irradiated with the laser beam along a moving direction of the laser beam; an imaging processing step of imaging the measured value of the intensity of the light corresponding to the moving direction of the laser beam to create a second image; and a determination step of determining the state of the welding portion based on a determination image including the first image and the second image.

[0068] Configuration 2: In the welding state determination method described in Configuration 1, the determination method further comprises a step of normalizing the measured value of the light intensity to create parameters for imaging, and in the imaging processing step, the second image is created using the parameters.

[0069] Configuration 3: In the determination method described in Configuration 1 or 2, the determination method further comprises a step of creating the determination image by combining the first image and the second image.

[0070] Configuration 4: In the determination method according to any one of Configurations 1 to 3, the measured values ​​of the intensity of the light imaged in the imaging step include measured values ​​of the intensity of plasma light obtained by spectroscopically analyzing light emitted from the welded member.

[0071] Configuration 5: In the determination method according to any one of Configurations 1 to 4, the measured values ​​of the intensity of the light imaged in the imaging process step include measured values ​​of the intensity of heat radiation light obtained by spectroscopically analyzing the light emitted from the welded member.

[0072] Configuration 6: In the determination method according to any one of Configurations 1 to 5, the measured values ​​of the intensity of the light imaged in the imaging processing step include measured values ​​of the intensity of reflected light of the laser light obtained by spectroscopically analyzing light emitted from the welded member.

[0073] Configuration 7: In any one of the determination methods described in Configurations 1 to 6, the determination method further comprises a step of measuring the output of the laser irradiated onto the welded component along the moving direction of the laser, and in the imaging step, the measured value of the output of the laser is imaged corresponding to the moving direction of the laser to create a third image, and in the determination image, the third image is included together with the first image and the second image.

[0074] Configuration 8: In the determination method according to any one of Configurations 1 to 7, in the determination step, the state of the weld is determined based on learning data obtained by machine learning of the determination image.

[0075] Configuration 9: A welding state determination system, for determining the welding state of a welded portion formed by irradiating a welded portion with a laser beam that moves relative to the welded portion and melts and solidifies, the determination system comprising: an image acquisition unit that acquires a first image as an image of the welded portion; a light intensity measurement unit that measures the intensity of light emitted from the welded portion irradiated with the laser beam along a moving direction of the laser beam; an imaging processing unit that images the measured value of the light intensity corresponding to the moving direction of the laser beam to create a second image; and a determination unit that determines the state of the welded portion based on the first image and the second image.

[0076] 10: judgment system; 11: first processing unit; 12: second processing unit; 13: third processing unit; 20: camera; 21: sensor; 22: spectroscopic mechanism; 31: first image; 33, 34, 35: second image; 36: third image; 37: combined image; 38: pixel; 50: laser oscillator; 51: optical fiber; 52: laser head; 53: reflector; 100: sealing body; 101: lead wire; 102: welding part.

Claims

1. A method for determining a welding state, for determining a welding state of a welded portion formed by a laser beam being irradiated onto a welded member by relative movement of the welded member and melting and solidifying the welded member, the method comprising: a step of acquiring a first image as an image of the welded portion; a step of measuring the intensity of light emitted from the workpiece to be welded irradiated with the laser light along a moving direction of the laser light; An imaging processing step of imaging the measured value of the intensity of the light in correspondence with the moving direction of the laser light to create a second image; and A determination step of determining the state of the welded portion based on a determination image including the first image and the second image.

2. The method for determining the welding state according to claim 1, in, The determination method further comprises the step of normalizing the measured value of the light intensity to create a parameter for imaging. In the imaging processing step, the second image is created using the parameters.

3. The determination method according to claim 1, in, The determination method further includes the step of creating the determination image by combining the first image and the second image.

4. The determination method according to claim 1, in, The measured values ​​of the intensity of the light imaged in the imaging process step include measured values ​​of the intensity of plasma light obtained by spectroscopically splitting the light emitted from the workpiece to be welded.

5. The determination method according to claim 1, in, The measured values ​​of the intensity of the light imaged in the imaging process step include measured values ​​of the intensity of heat radiation light obtained by spectroscopically splitting the light emitted from the welded member.

6. The determination method according to claim 1, in, The measured values ​​of the intensity of the light imaged in the imaging process step include measured values ​​of the intensity of reflected light of the laser light obtained by spectroscopically splitting the light emitted from the workpiece to be welded.

7. The determination method according to claim 1, in, The determination method further comprises the step of measuring the output of the laser beam irradiated to the welded member along the moving direction of the laser beam. In the imaging processing step, the measured value of the output of the laser light is imaged corresponding to the moving direction of the laser light to create a third image. The determination image includes the third image together with the first image and the second image.

8. The determination method according to any one of claims 1 to 7, in, In the determination step, the state of the weld is determined based on learning data obtained by machine learning of the determination image.

9. A welding state determination system for determining the welding state of a welded portion formed by a laser beam being irradiated onto a welded member by relative movement with respect to the welded member and then melted and solidified, the determination system comprising: An image acquisition unit that acquires a first image as an image of the welding portion; a light intensity measuring unit for measuring the intensity of light emitted from the workpiece to be welded irradiated with the laser light along a moving direction of the laser light; an imaging processing unit that images the measured value of the intensity of the light in correspondence with the moving direction of the laser to create a second image; and The determination unit determines a state of the welded portion based on the first image and the second image.

Images