Processing state determination method and determination device

By detecting the optical signal changes in the welding site, and using the training model to determine the workpiece gap, the problem of determining the gap in the overlap welding is solved, and the welding quality control is improved.

CN119031992APending Publication Date: 2024-11-26PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202380035350.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-05-10
Filing Date
2023-01-31
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

During laser welding, the gap between the workpieces during overlap welding results in unqualified joints, and it is difficult for the prior art to determine the existence of the gap in detail, affecting the welding quality.

Method used

Use a light sensor to detect the thermal radiation, visible and reflected light components of the welding site, calculate the characteristic amount of signal intensity changes, and determine whether the gap between the workpieces exists or not.

Benefits of technology

The detailed determination of the overlapping welding processing status is achieved, and the accuracy and efficiency of welding quality control is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119031992A_ABST
    Figure CN119031992A_ABST
Patent Text Reader

Abstract

The method for determining the machining state includes: a step for detecting, using an optical sensor, at least one component among heat radiation, visible light, and reflected light generated in a welded portion formed on the surface of a workpiece by irradiating the workpiece with laser light; a step for acquiring a signal indicating a change in at least one component in a time interval from the start of welding of the workpiece to the end of welding; a step for calculating a feature amount on the basis of the signal strength of the signal in a given interval among the time intervals; a step for inputting the calculated feature amount into a determination model for determining the processing state, and determining the amount of a gap occurring between the overlapping surfaces of the workpiece in the laser irradiation direction as the processing state; and a step for outputting the determined gap amount as a determination result. The determination model is constructed on the basis of training data including, in association with each other, a feature amount calculated under a plurality of conditions in which the machining state changes and an observed gap amount.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to a method and a device for determining a processing state in laser processing for overlap welding. Background Art

[0002] Patent document 1 discloses the following method: It is applied to laser welding in which a laser beam repeatedly generated in a pulsed form is irradiated on a workpiece, and the welding state such as pass / fail of each workpiece is determined. The method of patent document 1 detects the intensity of plasma light and reflected light released from the workpiece during laser welding as the detected light intensity, and extracts a characteristic value for each pulse of the laser based on the detected light intensity in a pre-set extraction interval from one cycle corresponding to one pulse of the laser. As the characteristic value, the average value or the variation amount based on the differential processing of the detected light intensity is calculated. The method of patent document 1 compares the extreme value of the characteristic value of each pulse repeatedly generated, i.e., the lower limit value of the reflected light or the upper limit value of the plasma light, with the pre-set threshold value of the characteristic value of the qualified product and the defective product for each workpiece, thereby determining the welding defect as the welding state.

[0003] Prior Art Literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2000-153379 Summary of the invention

[0006] In laser welding, due to changes in the processing state such as a gap between the overlapping surfaces of the workpieces (workpieces) in the irradiation direction of the laser, the joint area is reduced, which sometimes causes a failed joint. In such a case, in order to understand the cause of the failed joint, a detailed analysis of the processing state is required. On the other hand, in the determination of welding defects based on a given threshold value that separates the pass / fail of welding for each workpiece, such as in Patent Document 1, it is difficult to determine the detailed processing state such as the presence or absence of a gap between the workpieces during overlap welding.

[0007] The present disclosure provides a determination method and a determination device capable of determining in detail the processing state in laser processing for overlap welding.

[0008] According to one embodiment of the present disclosure, a method for determining a processing state in laser processing for overlap welding is provided. The method includes: a step of detecting at least one of the components of heat radiation, visible light, and reflected light generated in a welded portion formed on the surface of a processed object (workpiece) by irradiating a laser to the processed object (workpiece) using a light sensor; a step of acquiring a signal indicating a change in the at least one component in a time interval from the start of welding of the processed object to the end of welding; a step of calculating a feature quantity based on the signal intensity of the signal in a given interval in the time interval; a step of inputting the calculated feature quantity into a determination model for determining the processing state to determine the presence or absence of a gap between the overlapped surfaces of the processed object (between the workpieces) in the irradiation direction of the laser as the processing state; and a step of outputting the determined presence or absence of a gap as a determination result. The determination model is constructed based on training data, and the training data establishes associations including the feature quantities calculated under multiple conditions of processing state changes and the observed presence or absence of a gap.

[0009] According to one embodiment of the present disclosure, a device for determining a processing state in laser processing for overlap welding is provided. The determination device includes a calculation circuit and a communication circuit. The communication circuit receives a signal generated by a light sensor detecting at least one component of heat radiation, visible light, and reflected light generated in a welded portion formed on the surface of a workpiece by irradiating a laser to the workpiece (workpiece). The signal represents a change in the at least one component in a time interval from the start of welding of the workpiece to the end of welding. The calculation circuit includes: obtaining a signal through a communication circuit; a step of calculating a feature quantity based on the signal strength of the signal in a given interval in the time interval; a step of inputting the calculated feature quantity to a determination model for determining the processing state to determine the presence or absence of a gap between the overlapped surfaces of the workpiece (between the workpieces) in the irradiation direction of the laser as the processing state; and a step of outputting the determined presence or absence of a gap as a determination result. The determination model is constructed based on training data, and the training data includes the feature quantity calculated under multiple conditions of the processing state change and the observed presence or absence of a gap in a correlated manner.

[0010] According to the determination method and determination device of the present disclosure, the presence or absence of a gap between workpieces in the irradiation direction of laser light is determined, thereby making it possible to determine in detail the processing state in laser processing for overlap welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a diagram showing an overview of a determination system according to Embodiment 1 of the present disclosure.

[0012] Figure 2 This is a diagram illustrating the configuration of a laser processing device in a determination system.

[0013] Figure 3 This is a diagram illustrating an example of the configuration of a spectroscopic device in a determination system.

[0014] Figure 4 This is a block diagram illustrating the configuration of a determination device in the determination system.

[0015] Figure 5 This is a flowchart illustrating a determination process in the determination device.

[0016] Figure 6 This is a diagram for explaining a signal acquired in a determination device.

[0017] Figure 7 This is a diagram for explaining the processing of the determination model in the determination device.

[0018] Figure 8 This is a diagram for explaining the process of calculating the feature amount in the determination device.

[0019] Fig. 9 This is a flowchart illustrating the training process of the determination model.

[0020] Fig.10 This is a diagram for explaining the training data of the judgment model. DETAILED DESCRIPTION

[0021] The first embodiment of the present disclosure is a method for determining a laser processing state in laser processing for overlap welding, comprising: a step of detecting at least one of components of heat radiation, visible light, and reflected light generated in a welded portion formed on the surface of a workpiece by irradiating a laser to the workpiece using a light sensor; a step of acquiring a signal indicating a change in the component in a time interval from the start of welding to the end of welding of each of the workpieces; and a step of calculating a feature quantity based on the signal intensity of the signal in a given interval in the time interval; a step of inputting the calculated feature quantity into a determination model for determining the processing state to determine the presence or absence of a gap generated between the overlapped surfaces of the workpieces in the irradiation direction of the laser as the processing state; and a step of outputting the determined presence or absence of the gap as a determination result. The determination model is constructed based on training data, and the training data includes the feature quantity calculated under a plurality of conditions of the processing state change and the observed presence or absence of the gap in a correlated manner.

[0022] According to a second aspect of the present disclosure, in the method for determining a laser processing state according to the first aspect, the feature amount includes at least one of a signal intensity reduction amount indicating a degree of reduction in signal intensity of the reflected light and an integrated value of the signal intensity.

[0023] According to the third embodiment of the present disclosure, in the method for determining the laser processing state described in the second embodiment, the process of calculating the characteristic quantity also includes: a process of calculating the average intensity of a signal corresponding to the change of the reflected light in a time interval from the peak output after the rise to the fall of the laser output of the oscillating laser, the given interval includes: an interval calculated by setting the time when the signal of the reflected light first reaches the average intensity from the peak intensity as the initial time, and setting the time when the average intensity is reached again as the end time, and the signal intensity reduction amount is a value obtained by subtracting the lowest value of the signal intensity in the calculated interval from the average intensity.

[0024] According to the 4th embodiment of the present disclosure, in the method for determining the laser processing state described in any one of the 1st embodiment to the 3rd embodiment, the characteristic quantity includes a characteristic quantity corresponding to the time variation of the signal intensity of the reflected light in the time interval from the peak output after the rise of the laser output of the oscillating laser to the fall of the laser output.

[0025] According to the 5th embodiment of the present disclosure, in the method for determining the laser processing state described in any one of the 1st embodiment to the 4th embodiment, the characteristic quantity includes the integral value of the signal intensity of at least one of the thermal radiation and the visible light in the time interval from the peak output after the rise to the fall of the laser output of the oscillating laser.

[0026] According to the 6th embodiment of the present disclosure, in the method for determining the laser processing state described in any one of the 1st to 5th embodiments, the training data is further associated with the presence or absence of the gap and includes: a numerical value related to the melt width calculated by measuring the appearance shape of the weld part after welding, or an image of the weld part after welding; or both.

[0027] According to the 7th embodiment of the present disclosure, in the method for determining the laser processing state described in any one of the 1st embodiment to the 6th embodiment, the determination model includes a learning completion model generated by machine learning using training data, and the training data establishes an association between a feature value calculated from a signal obtained based on the component detected by performing the laser processing under each of a plurality of conditions under which the processing state changes, and the presence or absence of the gap under the each condition.

[0028] According to the 8th embodiment of the present disclosure, in the method for determining the laser processing state described in any one of the 1st embodiment to the 7th embodiment, the process of determining the presence or absence of the gap includes: determining the gap amount representing the size of the gap in the irradiation direction of the laser, the gap amount of the gap including: a numerical value representing the displacement amount taking the state in which the gap between the overlapping surfaces of the workpiece is not generated as a reference, and the training data of the determination model establishes an association between the feature amount calculated under the condition in which the gap is generated, and the gap amount of the generated gap.

[0029] According to a ninth aspect of the present disclosure, a laser processing state determination device is provided. The determination device is a processing state determination device for laser processing of overlap welding, and includes: an operation circuit; and a communication circuit, which receives a signal generated by a light sensor detecting at least one of the components of heat radiation, visible light, and reflected light generated in a welded portion formed on the surface of the workpiece by irradiating the workpiece with laser. The signal is a signal indicating the change of the component in a time interval from the start of welding to the end of welding of each of the workpieces. The operation circuit acquires the signal through the communication circuit, calculates a feature quantity based on the signal intensity of the signal in a given interval in the time interval, inputs the calculated feature quantity to a determination model for determining the processing state, determines the presence or absence of a gap generated between the overlapped surfaces of the workpieces in the irradiation direction of the laser, and outputs the determined presence or absence of the gap as the determination result. The determination model is constructed based on training data, and the training data includes the feature quantity calculated under a plurality of conditions of the processing state change and the observed presence or absence of the gap in a correlated manner.

[0030] The following describes the embodiments in detail with appropriate reference to the drawings. However, sometimes more detailed descriptions than necessary are omitted. For example, sometimes detailed descriptions of well-known matters and repeated descriptions of substantially the same structures are omitted. This is to avoid the following description from becoming unnecessarily lengthy and to make it easy for those skilled in the art to understand. In addition, the inventor provides the drawings and the following descriptions in order to enable those skilled in the art to fully understand the present disclosure, and does not limit the subject matter described in the patent claims.

[0031] (Implementation method 1)

[0032] In the first embodiment, as an example using the determination method and determination device according to the present disclosure, a determination system is described which detects components of light generated in laser processing for overlap welding and acquires signals based on the detected components to thereby determine the processing state.

[0033] 1. Structure

[0034] For the determination system involved in the first embodiment, use Figure 1 To explain. Figure 1 2 is a diagram showing an overview of a determination system 100 according to the present embodiment.

[0035] 1-1. System Overview

[0036] The determination system 100 includes a laser processing device 30 for performing laser processing for overlap welding, a spectrometer 40 for detecting light components, and a determination device 50. The determination device 50 is an example of the determination device involved in the present disclosure. The workpiece 70 for overlap welding is, for example, a workpiece made of metal, and includes two members 70a and 70b (hereinafter, the laser processing device 30 side is set as the upper side and is referred to as "upper member 70a" and "lower member 70b") that overlap in the irradiation direction of the laser 6. When the laser 6 is irradiated, thermal radiation in the near-infrared region caused by the temperature rise and luminescence or plasma luminescence inherent to the metal mainly of visible light components are generated. In addition, a part of the laser 6 that does not contribute to the processing is reflected as return light. In this way, when the laser 6 is irradiated from the laser processing device 30 to the workpiece 70, thermal radiation, visible light, and reflected light are generated in the molten portion 27, an example of a welded portion formed in the workpiece 70.

[0037] The generated light is focused in the laser processing device 30 and transmitted to the spectroscopic device 40 through the optical fiber 13 connecting the laser processing device 30 and the spectroscopic device 40. The light transmitted to the spectroscopic device 40 is split into components of thermal radiation, visible light, and reflected light, which are detected by the optical sensor 22 of the spectroscopic device 40 and converted into signals.

[0038] Here, for example, a gap F1 may be generated between the upper member 70a and the lower member 70b of the workpiece 70, resulting in welding failure. In this case, it is considered that the signal of each component changes in accordance with the generation of the gap F1. Therefore, if a signal is received from the spectroscopic device 40, the determination device 50 determines the presence or absence of the gap F1 as the processing state based on the signal, and outputs the determination result.

[0039] The determination device 50 of this embodiment determines the presence or absence of the gap F1 based on the size of the gap F1 in the irradiation direction of the laser 6, that is, the gap amount. For example, the state where the gap F1 does not occur is set as the reference value "0", and the gap amount of the gap F1 is specified by the displacement amount (+) from the upper surface of the lower member 70b to the lower surface of the upper member 70a in the overlapping surface of the workpiece 70. For example, when the gap amount is "0", it can be determined that there is no gap F1, and when the gap amount is not "0", it can be determined that there is a gap F1. The presence of the gap F1 is synonymous with the gap amount being greater than 0, and the absence of the gap F1 is synonymous with the gap amount being 0.

[0040] 1-2. Structure of laser processing device

[0041] Figure 2 The laser processing device 30 is a diagram illustrating the structure of the laser processing device 30 according to the present embodiment. The laser processing device 30 includes a laser oscillator 1 , a laser transmission optical fiber 2 , a lens barrel 3 , a collimator lens 4 , condenser lenses 5 and 11 , a first reflecting mirror 7 , and a second reflecting mirror 8 .

[0042] The laser oscillator 1 supplies, for example, a pulsed laser light 6 having a wavelength of about 1070 nanometers (nm). The light supplied from the laser oscillator 1 is amplified while being transmitted through the laser transmission optical fiber 2, and passes through a collimating lens 4 for obtaining a parallel beam to form the laser light 6, which travels straight in the lens barrel 3. The lens barrel 3 constitutes a processing head in the laser processing device 30.

[0043] The laser light 6 is reflected by the first reflector 7 except for a portion that is transmitted, and is focused by the focusing lens 5, and irradiated to the workpiece 70 fixed on the scanning table (not shown) by the pressing fixture 26. Thus, laser processing for overlap welding of the workpiece 70 is performed. In addition, the wavelength of the laser light 6 is not particularly limited to 1070 nm, and it is preferable to use a wavelength with a high absorption rate of the material.

[0044] When irradiated with the laser light 6, heat radiation from the workpiece 70, visible light due to plasma emission, and reflected light of the laser light 6 are generated in the molten portion 27. These light components pass through the first reflector 7, are reflected by the second reflector 8, and are condensed by the condenser lens 11, and then are transmitted to the spectroscopic device 40 through the optical fiber 13. In addition, a portion of the light transmitted through the second reflector 8 may be detected by a camera or a sensor.

[0045] 1-3. Structure of Spectroscopic Device

[0046] Figure 32 is a diagram illustrating the structure of the spectroscopic device 40 of the present embodiment. The spectroscopic device 40 includes a collimating lens 15, a third reflector 16, a fourth reflector 17, a fifth reflector 18, condenser lenses 19, 20, 21, a light sensor 22, a transmission cable 23, and a controller 24 inside a housing 28. The housing 28 prevents disturbance light from entering the inside of the spectroscopic device 40 from the outside and prevents light leakage from the inside.

[0047] The collimating lens 15 restores the light transmitted from the laser processing device 30 through the optical fiber 13 to parallel light. The third reflector 16 transmits visible light with a wavelength of 400nm to 700nm, for example, and reflects other components. The fourth reflector 17 reflects the reflected light of the laser 6 with a wavelength of about 1070nm, for example, and transmits other components. The fifth reflector 18 reflects thermal radiation with a wavelength of 1300nm to 1550nm, for example.

[0048] The light after passing through the collimating lens 15 is split into components of visible light, reflected light, and thermal radiation by the third reflector 16, the fourth reflector 17, and the fifth reflector 18, and is respectively focused by the focusing lenses 19 to 21. In addition, it is also possible to select the wavelength to be passed by arbitrarily configuring the optical paths after the third reflector 16, the fourth reflector 17, and the fifth reflector 18.

[0049] The optical sensor 22 includes, for example, optical sensors 22a, 22b, and 22c each having high sensitivity to a different wavelength. The optical sensors 22a, 22b, and 22c detect the components of visible light, reflected light, and thermal radiation collected by the collecting lenses 19 to 21, respectively, and generate an electrical signal corresponding to the intensity of the detected light. Alternatively, the optical sensor 22 may be composed of a single optical sensor capable of detecting the intensity of each wavelength.

[0050] The electrical signal generated by the optical sensor 22 is transmitted to the controller 24 via the transmission cable 23. The controller 24 is a hardware controller that performs overall control of the operation of the spectroscopic device 40. The controller 24 includes a CPU and a communication circuit, etc., and sends the electrical signal received from the optical sensor 22 to the determination device 50. The controller 24 has, for example, an A / D converter that converts the analog electrical signal into a digital signal (also referred to as "signal"). In addition, from the perspective of ensuring a sufficient number of samples in order to capture the characteristics of the processing technology and the tendency of the local value of the physical quantity in the determination of the processing state, the sampling period when converting to the digital signal is preferably, for example, less than 1 / 100 of the time for performing the output control of the laser 6.

[0051] 1-4. Structure of determination device

[0052] Figure 4 1 is a block diagram illustrating the structure of the determination device 50 of this embodiment. The determination device 50 is composed of an information processing device such as a computer. The determination device 50 includes a CPU 51 for performing calculations, a communication circuit 52 for communicating with other devices, and a storage device 53 for storing data and computer programs.

[0053] CPU51 is an example of an operation circuit of the determination device 50 in the present embodiment. CPU51 implements a given function including training and executing the determination model 57 by executing the control program 56 stored in the storage device 53. The determination device 50 implements the function of the determination device 50 in the present embodiment by executing the control program 56 by CPU51. In addition, in the present embodiment, the operation circuit constituting CPU51 may also be implemented by various processors such as MPU or GPU, or may be composed of one or more processors. In addition, the operation circuit may also be a hardware circuit such as a dedicated electronic circuit or a reconfigurable electronic circuit designed to implement the above-mentioned functions, or may be composed of various semiconductor integrated circuits such as GPGPU, TPU, DSP, microcomputer, FPGA and ASIC.

[0054] The communication circuit 52 is, for example, a communication circuit that communicates in accordance with standards such as IEEE802.11, 4G or 5G. The communication circuit 52 may also perform wired communication in accordance with standards such as Ethernet (registered trademark). The communication circuit 52 can be connected to a communication network such as the Internet. In addition, the determination device 50 can also communicate directly with other devices via the communication circuit 52, or can communicate via an access point. In addition, the communication circuit 52 can also be configured to be able to communicate with other devices without going through a communication network. For example, the communication circuit 52 may also include connection terminals such as a USB (registered trademark) terminal and an HDMI (registered trademark) terminal. The communication circuit 52, for example, receives various signals corresponding to the components of light detected from the spectroscopic device 40.

[0055] The storage device 53 is a storage medium for storing computer programs and data required to realize the functions of the determination system 100, and stores a control program 56 and various data executed by the CPU 51. The storage device 53 stores the signal received from the spectroscopic device 40, and stores the determination model 57 after the determination model 57 is constructed. The determination model 57 determines the gap amount of the gap F1 based on the signal from the spectroscopic device 40. The details of the determination model 57 will be described later.

[0056] The storage device 53 is composed of, for example, a magnetic storage device such as a hard disk drive (HDD), an optical storage device such as an optical disk drive, or a semiconductor storage device such as an SSD. The storage device 53 may also include a transient storage element composed of a RAM such as a DRAM or SRAM, and may also function as an internal memory of the CPU 51.

[0057] 2. Action

[0058] In the determination system 100 configured as described above, for example Figure 1 As shown, the spectroscopic device 40 uses the optical sensor 22 to detect the components of thermal radiation, visible light, and reflected light generated in the molten portion 27 by irradiation with the laser 6. The spectroscopic device 40 sends a signal corresponding to the intensity of each detected component to the determination device 50. The operation of the determination device 50 in the present system 100 is described below.

[0059] 2-1. Determination process

[0060] Below, use Figures 5 to 8 Next, a description will be given of a process of determining the gap amount of the gap F1 as a determination process of the machining state in the determination device 50 .

[0061] Figure 5 This is a flowchart illustrating the determination process in the determination device 50 of this embodiment. Each process shown in this flowchart is executed, for example, by the CPU 51 of the determination device 50. For example, when a user of the determination system 100 or the like inputs a predetermined operation for starting the determination process from an input device connected via the communication circuit 52, this flowchart is started.

[0062] First, the CPU 51 acquires, through the communication circuit 52 , signals corresponding to the components of thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 ( S1 ).

[0063] Figure 6 It is a diagram for explaining the signal acquired in the determination device 50. Figure 6 (A), (B), and (C) illustrate signal waveforms corresponding to the intensities of thermal radiation, visible light, and reflected light, respectively. Figure 6 (D) shows the output of the laser beam 6 irradiated onto the workpiece 70 . Figure 6 The signals (A) to (C) correspond to the thermal radiation, visible light, and reflected light generated by the laser output. Figure 6 In (A) to (D), the horizontal axis represents time and the vertical axis represents signal strength ( Figure 6 (A)~(C)) or laser output ( Figure 6(D)). In addition, the time interval T1 represents a time interval corresponding to one pulse of the laser light 6, and the time interval T2 represents a time interval of peak output excluding the rise and fall of the laser light output.

[0064] Here, in the laser processing device 30 of the present embodiment, welding is performed for each workpiece 70 within a time interval T1 corresponding to one pulse of the laser light 6. Figure 5 In step S1, CPU 51 obtains Figure 6 The signals showing changes in the components of the thermal radiation, visible light, and reflected light in the time interval T1 from the start to the end of welding of each workpiece 70 as exemplified in (A) to (C) of FIG.

[0065] Next, the CPU 51 calculates a feature quantity to be input to the determination model 57 based on the signal strength of the acquired signal (S2). The calculation of the feature quantity (S2) will be described in detail later.

[0066] After calculating the characteristic amount (S2), the CPU 51 inputs the calculated characteristic amount into the determination model 57 to determine the gap amount of the gap F1 (S3). In the present embodiment, in the determination model process (S3), the CPU 51 determines the numerical value representing the displacement amount between the overlapping surfaces of the workpiece 70 (also referred to as "between workpieces") as the gap amount. Alternatively, the gap amount may be determined as a category after the size of the gap amount is classified.

[0067] Figure 7 This is a diagram for explaining the process of determining the model ( S3 ). Figure 7 (A) Based on Figure 1 The waveforms of the signal intensities of the reflected light detected in each welding process when the gap amount of the gap F1 is “0” or on the positive (+) side with the same reference displacement amount are shown. Figure 7 (B) for Figure 7 (A) is a waveform showing the intensity of each signal detected in the same manner as thermal radiation or visible light. Figure 7 (C) shows the gap amount of the gap F1 and the positional relationship between the members 70 a and 70 b of the workpiece 70 .

[0068] The processing of the decision model (S3) is based on Figure 7 The corresponding relationship between the signal waveform and the gap amount of the gap F1 is determined by using the judgment model 57 that has been learned. Figure 7 To illustrate the knowledge obtained by the inventors of the technology in this disclosure.

[0069] like Figure 7As shown in (A), if the gap F1 is generated, the signal intensity of the reflected light will temporarily decrease, and the amount of decrease in the signal intensity will increase in accordance with the increase in the gap amount. The reason for this is that at the beginning of the welding process, the surface of the workpiece 70 is melted and evaporated by the irradiation of the laser 6, thereby forming a cavity (keyhole) on the surface. Regarding the signal waveform of the reflected light, it is believed that when the laser 6 melts the upper member 70a and the lower member 70b of the workpiece 70, light leakage from the keyhole to the gap F1 and burn-through of the molten portion 27 occur in the molten portion 27, so the signal intensity decreases.

[0070] In addition, if Figure 7 As shown in (B), regarding the signal waveforms of the thermal radiation light and the visible light, if the gap amount of the gap F1 increases, the signal intensity decreases as a whole, and the decrease in the signal intensity increases in accordance with the increase in the gap amount. During laser welding, heat input based on the laser 6 is required, but if the gap amount of the gap F1 increases, light leakage occurs relative to the gap F1 when the keyhole is formed, and the molten portion 27 burns through. Therefore, it is believed that the signal intensity decreases due to the decrease in the area where the thermal radiation light and the visible light are emitted.

[0071] Based on the above knowledge, the inventors have inferred that the gap amount of the gap F1 can be predicted based on a signal corresponding to at least one of the components of thermal radiation, visible light, and reflected light, and using feature quantities such as signal intensity. Therefore, the inventors used training data that established a correspondence between these feature quantities and the gap amount of the gap F1 to construct a determination model 57, and performed determination processing using the determination model 57.

[0072] According to the determination model 57 constructed in this way, when the feature amount (S2) calculated based on the acquired signal (S1) is input, the determination result of the gap amount of the gap F1 is output (S3). The process of constructing the determination model 57 will be described later.

[0073] Back to Figure 5 The CPU 51 uses the communication circuit 52 to output the determination result (S4) of the gap F1 determined by the processing (S3) of the determination model. The determination result can be received and displayed by an external information processing device or a display device, for example. In addition, the determination device 50 can also include a display device (such as a display) that can communicate with the CPU 51, and display the determination result on the display device.

[0074] After that, CPU51 ends Figure 5 For example, the following flowchart is repeatedly executed each time a welding process is performed on each workpiece 70. Figure 5 Flowchart of the process.

[0075] According to the above determination process, the determination device 50 of the present embodiment acquires the signal (S1) generated by the optical sensor 22 of the spectroscopic device 40, calculates the characteristic amount (S2) based on the signal intensity, and inputs the calculated characteristic amount (S3) to the determination model 57 for determining the gap amount of the gap F1. Thus, the determination device 50 can determine the gap amount of the gap F1 of the laser 6 in detail as the processing state in the laser processing for overlap welding.

[0076] 2-1-1. Calculation of feature quantity

[0077] for Figure 5 Details of step S2, using Figure 8 To explain. Figure 8 This is a diagram for explaining the process ( S2 ) of calculating the feature amount in the determination device 50 . Figure 8 (A) and (B) are in Figure 6 Similarly, the vertical axis and the horizontal axis show the time change of the signal intensity of the signal corresponding to the reflected light. Figure 8 (A) corresponds to the reflected light without the gap F1, Figure 8 (B) corresponds to the reflected light in the case where there is a gap F1. After the CPU 51 acquires the signal (S1), in step S2, for example, a smoothing process is performed by applying a smoothing filter to the signal. By smoothing, for example, it is possible to easily obtain a signal waveform (see Figure 6 ) to calculate the feature quantity.

[0078] When the laser beam 6 is irradiated, as described above, the surface of the workpiece 70 melts and evaporates, thereby forming a cavity on the surface, that is, a keyhole. When the reflected light generated when the laser beam 6 is irradiated generates a gap F1, light leakage occurs from the overlapped surface of the workpiece 70 (that is, the interface of the workpiece) when the keyhole is formed, and the molten portion 27 is burned through. Therefore, Figure 8 As shown in (B), light intensity decreases particularly when keyholes are formed. Therefore, in step S2, the determination device 50 of this embodiment first calculates the amount of decrease in signal intensity corresponding to the decrease in light intensity, that is, the amount of signal intensity decrease as a feature amount.

[0079] In this embodiment, from the viewpoint of making the feature value reflect the decrease in signal strength due to the generation of the gap F1 with high accuracy, for example, Figure 8The amount of reduction in signal intensity is calculated by using the average value of the signal intensity of the signal acquired under the condition that it is determined that no gap F1 is generated as in (A) as a reference. For example, the CPU 51 acquires the signal in advance, calculates the average value Va of the signal intensity in the time interval T2 when the laser 6 outputs the peak value for the reflected light component, and stores it in the storage device 53. For example, the CPU 51 uses the signal after calculating the average value Va to pre-set the time interval Ts for measuring the reduction in the intensity of the signal acquired in step S1. The time interval Ts is an interval calculated by setting the time when the signal intensity first reaches the average value Va from the initial peak as the initial time, and the time when the signal intensity reaches the average value Va again as the end time, and is set to the period from the initial time to the end time.

[0080] exist Figure 5 In step S2, the CPU 51 performs, for example, a calculation process of subtracting the minimum value Vb of the signal strength of the signal acquired in step S1 from the average value calculated in the preset time interval Ts. As a result, it is possible to extract the amount of signal strength reduction corresponding to the generation of the gap F1, that is, information on the difference in signal strength based on the presence or absence of the gap F1. In addition, regarding the size of the difference, it is considered that the difference corresponding to the gap amount of the gap F1 can be extracted corresponding to the amount of reduction in the signal strength of the reflected light. In addition, for example, each time step S2 is executed, a process of unifying the setting time of the time interval Ts for calculating the average value Va and the rising time of the signal waveform may be performed.

[0081] Furthermore, in this embodiment, Figure 5 In step S2, the CPU 51 further calculates the integral value of the signal intensity of the reflected light in the time interval Ts as a feature value. Thus, in addition to the decrease in signal intensity based on the difference from the average value Va, the integral value is also used as a feature value, so that even when a sudden abnormal value of signal intensity occurs, the gap amount of the gap F1 can be determined more robustly.

[0082] Furthermore, in this embodiment, Figure 5 In step S2, the CPU 51 further calculates the variance value of the signal intensity of the reflected light in the time interval T2 when the output of the laser 6 is the peak output. Regarding the gap F1, the variance value of the signal intensity, that is, the time variation of the amplitude of the signal waveform, tends to increase in proportion to the increase in the gap amount, so by using the variance value as a feature value, the gap amount can be determined with higher accuracy.

[0083] Furthermore, in this embodiment, Figure 5In step S2, the CPU 51 further calculates the integral value of the signal intensity in the time interval T2 for the reflected light, thermal radiation light, and visible light generated when the laser 6 is irradiated. When the gap F1 is generated, the molten portion 27 is burned through, so the thermal radiation light and visible light in particular are easy to reflect the change in the molten state of the material of the workpiece 70, so that the light intensity decreases. In this way, as the gap amount increases, the signal intensity of each light component decreases. Therefore, by using the integral value of each signal intensity as a feature amount, the change in the luminous energy of the gap F1 can be reflected with high accuracy and judgment can be made.

[0084] Furthermore, the appearance shape of the molten portion 27 on the surface of the upper member 70a after welding can also be measured. In step S2, the CPU 51 can also calculate the characteristic amount of the measurement information of the molten width of the molten portion 27 in the measurement result or the image of the appearance shape. The molten width is defined as the width of the molten portion 27 in the direction perpendicular to the advancing direction of the welding process. When the gap F1 is generated, the burn-through of the molten portion 27 occurs, and the molten width of the molten portion 27 formed thereby decreases in proportion to the burn-through amount. Therefore, it is considered that the gap amount of the gap F1 can be determined with high accuracy by measuring the appearance shape of the molten portion 27 after welding and using the molten width or the image information of the appearance shape as the characteristic amount. For example, by using the molten width of the molten portion 27 as the characteristic amount, the change of the luminous energy corresponding to the gap amount of the gap F1 can be reflected with high accuracy and determined.

[0085] In addition, Figure 5 In step S2, only a part of the above-mentioned feature quantities may be calculated, or any combination of the feature quantities may be calculated. In addition, the integral value of the signal intensity may be calculated only for the components of the thermal radiation, visible light, and part of the reflected light as the feature quantity.

[0086] 2-2. Training Process

[0087] Next, for the training process for constructing the determination model 57, the following is used: Fig. 9 as well as Fig.10 To explain.

[0088] Fig. 9 This is a flowchart illustrating the training process of the determination model 57. Each process in this flowchart is executed by the CPU 51 of the determination device 50, for example.

[0089] First, the CPU 51 acquires training data stored in advance in, for example, the storage device 53 ( S11 ).

[0090] Fig.10: is a diagram for explaining the training data D1 of the determination model 57. The training data D1 is data in which a correspondence is established between feature quantities such as the integral value of the signal waveform of the thermal radiation and visible light, the amount of decrease in the signal intensity of the reflected light, and the signal intensity of each of these components (not shown), and the gap amount of the gap F1. The feature quantity is calculated based on the signal obtained by the components of the thermal radiation, visible light, and reflected light detected by actually performing laser processing under multiple conditions in which the gap F1 changes, and is recorded in association with the gap amount of the gap F1 measured under each condition, thereby constructing the training data D1. The training data D1 may also include, in association with the gap amount of the gap F1, a molten width obtained by measuring the appearance shape of the molten portion 27 after welding and / or an image of the appearance shape.

[0091] Back to Fig. 9 When the CPU 51 obtains the training data D1 (S11), it uses the training data D1 to perform machine learning and generates a determination model 57 (S12). The determination model 57 is generated, for example, as a regression model based on linear regression, Lasso regression, ridge regression, decision tree, random forest, gradient boosting, support vector regression, Gaussian process regression, neural network, or k-nearest neighbor method.

[0092] According to the above training process ( S11 - S12 ), the determination model 57 can be generated as a learned model for determining the gap amount of the gap F1 based on feature amounts calculated based on signals corresponding to components of thermal radiation, visible light, and reflected light detected during the laser welding process.

[0093] In addition, the training process of the determination model 57 may be performed in an information processing device different from the determination device 50. The determination device 50 may also obtain the constructed determination model through the communication circuit 52 via a communication network, for example. In addition, the training data of the determination model 57 may also include various feature quantities as described above and the presence or absence of the gap F1 or the classification category indicating the size of the gap amount in association. In this case, the determination model 57 may be generated as various classification models using the training data.

[0094] 3. Effects, etc.

[0095] As described above, in the present embodiment, the determination process (S1 to S4) provides a determination method for the processing state in the laser processing for overlap welding (a determination method for the laser processing state). The method includes: a step of detecting at least one of the components of heat radiation, visible light, and reflected light generated in the molten portion 27 (an example of a welded portion) formed on the surface of the workpiece 70 by irradiating the laser 6 to the workpiece 70 using the optical sensor 22; a step of acquiring a signal representing a change in the component within a time interval T1 as an example of a time interval from the start of welding to the end of welding of each workpiece 70 (S1); a step of calculating a feature quantity based on the signal intensity of the signal within a given interval in the time interval T1 (S2); a step of inputting the calculated feature quantity into the determination model 57 for determining the processing state to determine the gap amount as an example of the presence or absence of the gap F1 in the irradiation direction of the laser 6 as the processing state (S3); and a step of outputting the determined gap amount of the gap F1 as a determination result (S4). The determination model 57 is constructed based on the training data D1 which includes, in association with each other, feature quantities calculated under a plurality of conditions in which the machining state changes and observed backlash quantities.

[0096] According to the above method, a signal based on at least any one of the thermal radiation, visible light, and reflected light generated and detected by irradiation of the laser 6 is acquired (S1), a feature value is calculated based on the signal intensity (S2), and a determination is performed (S3) using the determination model 57. Thus, the machining state can be determined in detail by using the determination model 57 constructed by using the training data D1 that associates the feature value based on the signal intensity with the gap amount of the gap F1 as the machining state.

[0097] In this embodiment, the feature value includes at least one of a signal intensity reduction amount indicating a degree of reduction in the signal intensity of the reflected light and an integrated value of the signal intensity. This makes it easy to reflect changes in signal intensity accompanying the generation of the gap F1 in the determination of the determination model 57.

[0098] In the present embodiment, the step of calculating the characteristic quantity (S2) further includes: a step of calculating the average value Va as an example of the average intensity of the signal corresponding to the change of the reflected light in the time interval T2 from the rise of the laser output of the oscillating laser 6 to the fall of the peak output. The given interval in the present embodiment includes a time interval Ts calculated by setting the time when the signal of the reflected light first reaches the average value Va from the peak intensity as the initial time and the time when the average value Va is reached again as the end time. The signal intensity reduction amount is a value obtained by subtracting the lowest value Vb of the signal intensity in the time interval Ts from the average value Va (refer to Figure 8 ). Thus, for example, by calculating the average value Va in the signal when the gap F1 does not occur and calculating the minimum value Vb in the signal of the object for determining the presence or absence of the gap F1, the difference in signal strength caused by the presence or absence of the gap F1 can be calculated as the signal strength reduction amount.

[0099] In this embodiment, the characteristic quantity includes a variance value of the amplitude of the signal waveform representing the signal intensity as an example of a characteristic quantity corresponding to the time variation of the signal intensity of the reflected light in the time interval T2 when the laser output has a peak output. Thus, it is possible to reflect the tendency that the time variation of the amplitude of the signal waveform increases in accordance with the increase in the gap amount of the gap F1, thereby determining the gap amount with higher accuracy.

[0100] In this embodiment, the characteristic amount includes the integral value of the signal intensity of at least one of the thermal radiation and the visible light in the time interval when the laser 6 outputs the peak value. Figure 7 As shown in (B) and (C) of FIG. 1 , the tendency that the signal intensity decreases as the gap amount of the gap F1 increases while the laser output is continued can be reflected, and the gap amount of the gap F1 can be easily determined.

[0101] In the present embodiment, the training data D1 of the determination model 57 further includes, in association with the gap amount as an example of the presence or absence of the gap F1, a numerical value related to the fusion width calculated by measuring the appearance shape of the fusion portion 27 (an example of the welded portion) after welding, or an image of the fusion portion 27, or both. According to the determination model 57 constructed using such training data D1, the gap amount can be determined by using the fusion width and / or the image of the appearance shape of the fusion portion 27 as a feature amount.

[0102] In the present embodiment, the determination model 57 includes a learning model (S11-S12) generated by machine learning using training data D1, which associates a feature amount calculated based on a signal obtained by performing laser processing on a plurality of conditions in which the gap amount of the gap F1 changes as an example of a processing state, and the gap amount as an example of the presence or absence of the gap F1 under each condition. Thus, the determination model 57 can be obtained as a processing state by determining the gap amount of the gap F1 based on the feature amount calculated based on the signal of the detected component.

[0103] In the present embodiment, the step (S3) of determining the presence or absence of a gap includes determining the gap amount indicating the size of the gap F1 in the irradiation direction of the laser 6. The gap amount of the gap F1 includes a numerical value indicating the displacement amount of a state where the gap F1 between the overlapping surfaces of the workpiece 70 is not generated as a reference "0". The training data D1 of the determination model 57 includes the feature amount calculated in the state where the gap F1 is generated and the gap amount of the generated gap F1 in association with each other. Thus, the processing state in the laser processing can be determined in detail, including the extent to which the gap F1 is generated in the irradiation direction of the laser 6.

[0104] In the present embodiment, the components detected by the optical sensor 22 include thermal radiation and visible light. Thus, the integral value of the signal waveform of the signal corresponding to the thermal radiation and the visible light can be used as the feature amount. For example, the change in the melting state of the workpiece 70 is easily reflected in these components, so the gap amount of the gap F1 can be easily determined with high accuracy.

[0105] In this embodiment, the components detected by the optical sensor 22 include reflected light. Therefore, the integral value of the signal intensity of the signal corresponding to the reflected light can be used as the feature amount. Compared with other components, the time variation of the signal intensity of the signal of the reflected light, that is, the fluctuation of the signal intensity is small, so the gap amount of the gap F1 can be easily determined with high accuracy.

[0106] In the determination system 100 of the present embodiment, the determination device 50 is an example of a determination device for the processing state in the laser processing for overlap welding. The determination device 50 includes a CPU 51 as an example of a calculation circuit, and a communication circuit 52. The communication circuit 52 receives a signal generated by the optical sensor 22 detecting at least one component of the components of thermal radiation, visible light, and reflected light generated in the molten portion 27 (an example of a welded portion) formed on the surface of the workpiece 70 by irradiating the laser 6 to the workpiece 70. The signal is a signal indicating a change in the component in the time interval T1 as an example of a time interval from the start of welding to the end of welding of each workpiece 70. The CPU 51 acquires the signal through the communication circuit 52 (S1), calculates the feature quantity based on the signal strength in a given interval in the time interval T1 (S2), inputs the calculated feature quantity to the determination model 57 for determining the processing state, determines the gap quantity as an example of the presence or absence of the gap F1 in the irradiation direction of the laser 6 as the processing state (S3), and outputs the determined gap quantity of the gap F1 as the determination result (S4). The gap quantity of the gap F1 is determined based on the state in which no gap is generated when the laser 6 is irradiated to the workpiece 70 as a reference "0". The determination model 57 is constructed based on the training data D1, and the training data D1 establishes associations including the feature quantity calculated under multiple conditions of the processing state change and the gap quantity as an example of the observed presence or absence of the gap F1.

[0107] According to the above-described determination device 50 , the above-described determination method can be executed to determine in detail the processing state in the laser processing for overlap welding.

[0108] (Other Implementations)

[0109] As described above, the above-mentioned embodiments are described as examples of the technology disclosed in this application. However, the technology in the present disclosure is not limited thereto, and can also be applied to embodiments that are appropriately changed, replaced, added, omitted, etc. In addition, each component element described in each of the above-mentioned embodiments can also be combined to form a new embodiment.

[0110] In the above-mentioned first embodiment, as a feature quantity, in addition to the decrease in signal intensity and the integral value in the time interval Ts of the signal corresponding to the reflected light, the determination device 50 also calculates the integral value of the signal intensity of the reflected light, the thermal radiation light, and the visible light in the time interval T2 when the peak value is output, etc. (S2). In this embodiment, the feature quantity is not particularly limited to this, for example, it may be only the decrease in signal intensity in the time interval Ts, or it may not include either the decrease in signal intensity or the integral value. In addition, regarding the feature quantity, for example, for the signal intensity in the time interval T2, it may be that the integral value of either or both of the thermal radiation light and the visible light is not included, but the integral value is included.

[0111] In the above-mentioned first embodiment, the determination device 50 calculates the feature value by smoothing the signal waveform according to the signal strength in advance when calculating the feature value (S2). In the present embodiment, the feature value may be calculated without applying the smoothing process to the signal waveform.

[0112] In the above-mentioned first embodiment, in the calculation of the characteristic amount (S2), when calculating the signal intensity reduction amount, an example is described in which the average value Va of the signal intensity of the reflected light is calculated based on the signal intensity of the reflected light when the gap F1 is not generated. In this embodiment, the average value of the signal intensity is not necessarily limited to being calculated based on the signal intensity when there is no gap F1, and can also be calculated based on the signal intensity when there is a gap F1. In this case, the signal intensity reduction amount calculated based on the average value can be used as a characteristic amount to construct the determination model 57.

[0113] In the above-mentioned first embodiment, the determination device 50 calculates the integral value of the signal intensity of the reflected light, thermal radiation, and visible light as the feature quantity (S2). In this embodiment, the feature quantity of the integral value of the signal intensity may be calculated based on a signal of a part of the reflected light, thermal radiation, or visible light, for example, the material may be selected by taking into account the absorptivity of the material to the wavelength of the laser light output from the laser oscillator 1 of the laser processing device 30.

[0114] The present disclosure is not limited to the above-mentioned embodiments, and various modifications are possible. That is, embodiments obtained by combining technical means appropriately modified by those skilled in the art are also within the scope of the present disclosure.

[0115] Industrial Applicability

[0116] The present disclosure can be applied to a system for determining a processing state in laser processing for overlap welding, and can be applied particularly to a method and apparatus for determining the amount of gap between workpieces.

[0117] Description of Reference Numerals

[0118] 1 Laser oscillator

[0119] 2 Optical fiber for laser transmission

[0120] 3. Lens tube

[0121] 4 Collimating lens

[0122] 5.11 Condenser lens

[0123] 6 Laser

[0124] 7 1st reflector

[0125] 8 Second reflector

[0126] 13. Fiber Optics

[0127] 15 Collimating lens

[0128] 16 3rd reflector

[0129] 17 4th Reflector

[0130] 18 5th Reflector

[0131] 19, 20, 21 Condenser lens

[0132] 22 Light Sensor

[0133] 23 Transmission Cable

[0134] 24 Controller

[0135] 26 Press fixture

[0136] 27 Melting section

[0137] 30 Laser processing equipment

[0138] 40 Spectroscopic Device

[0139] 50 Determination device

[0140] 51 CPU

[0141] 52 Communication circuit

[0142] 53 Storage device

[0143] 56 Control Program

[0144] 57 Determination Model

[0145] 70 Workpiece

[0146] F1 Clearance

[0147] D1 Training data

[0148] 100 judgment system.

Claims

1. A method for determining a processing state is a method for determining a processing state in a laser process for overlap welding, comprising: The step of detecting at least one of components of heat radiation, visible light, and reflected light generated in a weld formed on a surface of a workpiece by irradiating the workpiece with laser light using a light sensor; A step of acquiring a signal indicating a change in the at least one component in a time interval from the start of welding to the end of welding of the workpiece; A step of calculating a feature value based on a signal strength of the signal within a given interval among the time intervals; Inputting the calculated feature amount to a determination model for determining the processing state to determine the presence or absence of a gap generated between overlapping surfaces of the workpiece in the irradiation direction of the laser as the processing state; and a step of outputting the presence or absence of the gap determined as a determination result, The determination model is constructed based on training data, and the training data includes the feature amount calculated under a plurality of conditions under which the machining state changes and the observed presence or absence of the gap in a correlated manner.

2. The method for determining a processing state according to claim 1, wherein: The feature amount includes at least one of a signal intensity reduction amount indicating a degree of reduction in the signal intensity of the reflected light and an integrated value of the signal intensity.

3. The method for determining a processing state according to claim 2, wherein: The step of calculating the characteristic amount includes the step of calculating an average intensity of a signal corresponding to a change in the reflected light in a time interval from a rise in the laser output of the oscillating laser to a fall in a peak output, The given interval includes: an interval calculated by setting the time when the signal of the reflected light reaches the average intensity from the peak intensity as the initial time and the time when the signal reaches the average intensity again as the end time, The signal strength reduction amount is a value obtained by subtracting the calculated lowest value of the signal strength in the interval from the average strength.

4. The method for determining a processing state according to claim 1, wherein: The feature amount includes a feature amount corresponding to a time variation in the signal intensity of the reflected light in a time interval from after the rise of the laser output of the oscillating laser light to before the fall at the time of peak output.

5. The method for determining a processing state according to claim 1, wherein: The feature amount includes an integrated value of the signal intensity of at least one of the thermal radiation and the visible light in a time interval from after the rise of the laser output of the laser beam to before the fall at the peak output.

6. The method for determining a processing state according to claim 1, wherein: The training data further includes, in association with the presence or absence of the gap, a numerical value related to a fusion width calculated by measuring an external shape of the welded portion after welding, or an image of the welded portion after welding.

7. The method for determining a processing state according to claim 1, wherein: The training data further includes, in association with the presence or absence of the gap, both a numerical value related to a fusion width calculated by measuring an external shape of the welded portion after welding and an image of the welded portion after welding.

8. The method for determining a processing state according to claim 1, wherein: The determination model includes a learning completion model generated by machine learning using training data, wherein the training data establishes an association between a feature value calculated based on a signal obtained by performing the laser processing on at least one component detected under each of a plurality of conditions under which the processing state changes, and the presence or absence of the gap under the each condition.

9. The method for determining a processing state according to any one of claims 1 to 8, wherein: The step of determining whether the gap exists includes: determining a gap amount indicating a size of the gap in an irradiation direction of the laser beam; The gap amount of the gap includes a numerical value indicating a displacement amount based on a state where the gap is not generated between the overlapping surfaces of the workpieces, The training data of the determination model includes the feature amount calculated under the condition where the gap occurs and the gap amount of the generated gap in association with each other.

10. A processing state determination device is a processing state determination device used in laser processing of overlap welding, comprising: an operational circuit; and a communication circuit receiving a signal generated by detecting, by an optical sensor, at least one of components of heat radiation, visible light, and reflected light generated in a welded portion formed on a surface of a workpiece by irradiating a laser beam to the workpiece, The signal is a signal indicating a change in the at least one component in a time interval from the start of welding to the end of welding of the workpiece, The operation circuit performs the following operations: acquiring the signal through the communication circuit; Calculating a feature quantity based on a signal strength of the signal within a given interval in the time interval; Inputting the calculated feature amount into a determination model for determining the processing state, and determining the presence or absence of a gap generated between overlapping surfaces of the workpiece in the irradiation direction of the laser as the processing state; The presence or absence of the gap is output as a determination result, The determination model is constructed based on training data, and the training data includes the feature amount calculated under a plurality of conditions under which the machining state changes and the observed presence or absence of the gap in a correlated manner.

Citation Information

Patent Citations

  • Method for discriminating welded state of laser welding and device therefor

    JP2000153379A