Method and apparatus for determining laser processing state

Abstract

This machining condition determination method includes a step of using an optical sensor to detect at least one of thermal radiation light, visible light, and reflected light generated in a welded portion formed on the surface of a workpiece by irradiating the workpiece with laser light, as step of acquiring a signal indicating a change in at least one of thermal radiation light, visible light, and reflected light in a time interval that corresponds to the welding time of each workpiece, a step of calculating a feature amount including the slope of a straight line that approximates the signal waveform of a signal in a predetermined interval of the time interval, a step of inputting the calculated feature amount to a determination model that determines the machining state, and determining, as the machining state, deviation that includes the distance of the focal position in the irradiation direction of the laser beam, and a step of outputting, as the determination result, the deviation of the determined focal position. The determination model is built on the basis of training data that includes correlation of the feature amount calculated under conditions in which deviation of the focal position is occurring and the deviation of the focal position that has occurred.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 is applied to a laser welding method in which a laser beam generated in a pulsed manner is irradiated onto a workpiece to perform welding, and discloses a method for determining a welding state such as good / bad welding in a workpiece, a method for determining a welding state of laser welding, etc. The method of Patent Document 1 detects the intensities of plasma light and reflected light emitted from the workpiece during laser welding as detection light intensities, and extracts a pulse-by-pulse feature value for each pulse of the laser beam based on the detection light intensity in a preset extraction section out of one cycle of the detection light intensity corresponding to one pulse of the laser beam. As the pulse-by-pulse feature value, an average value of the detection light intensity, a change amount by differential processing, an amplitude by differential processing, etc. are calculated. The method of Patent Document 1 obtains a lower limit value or an upper limit value of the pulse-by-pulse feature value as an extreme value, compares the extreme value with a predetermined threshold value, and determines the occurrence of a welding defect as the welding state for each workpiece.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] According to one aspect of the present disclosure, a method for determining a processing state in laser processing for overlay welding is provided. The method includes a step of using an optical sensor to detect at least one of thermal radiation light, visible light, and reflected light generated at a welded portion formed on the surface of a workpiece by irradiating the workpiece with laser light; a step of acquiring a signal indicating a change in at least one of thermal radiation light, visible light, and reflected light in a time interval corresponding to the welding time for each workpiece; a step of calculating a feature amount including the slope of a straight line approximating the signal waveform of the signal in a predetermined interval of the time interval; a step of inputting the calculated feature amount into a determination model for determining the processing state, and determining, as the processing state, a deviation including the distance of the focal position in the irradiation direction of the laser light; and a step of outputting the determined deviation of the focal position as a determination result. The determination model is constructed based on training data including the feature amounts calculated under the condition that a deviation of the focal position has occurred and the generated deviation of the focal position associated with each other.

[0005] According to one aspect of the present disclosure, a determination device for a processing state in laser processing for overlay welding is provided. The determination device includes an arithmetic circuit and a communication circuit. The communication circuit receives a signal generated by detecting, by an optical sensor, at least one of thermal radiation light, visible light, and reflected light generated at a welded portion formed on the surface of a workpiece by irradiating the workpiece with laser light. The signal is a signal indicating a change in at least one of thermal radiation light, visible light, and reflected light in a time interval corresponding to the welding time for each workpiece. The arithmetic circuit acquires the signal through the communication circuit, calculates a feature amount including the slope of a straight line approximating the signal waveform of the signal in a predetermined interval of the time interval, inputs the calculated feature amount into a determination model for determining the processing state, determines, as the processing state, a deviation including the distance of the focal position in the irradiation direction of the laser light, and outputs the determined deviation of the focal position as a determination result through the communication circuit. The determination model is constructed based on training data including the feature amounts calculated under the condition that a deviation of the focal position has occurred and the generated deviation of the focal position associated with each other.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

DETAILED DESCRIPTION OF THE INVENTION

[0007] In laser welding, when the position of the focus in the irradiation direction of the laser beam deviates from the surface of the workpiece during laser irradiation, the bonding area may decrease due to a change in the processing state, resulting in a bonding defect. In such a case, while a detailed analysis of the processing state is required to investigate the cause of the bonding defect, it has been difficult to make a detailed determination of how the focus position has deviated in the method for determining the occurrence of welding defects.

[0008] The present disclosure provides a determination method and a determination apparatus capable of determining in detail the processing state in laser processing for overlap welding.

[0009] Hereinafter, embodiments will be described in detail with reference to the drawings as appropriate. However, a more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and duplicate descriptions of substantially the same configurations may be omitted. This is to avoid making the following description unnecessarily redundant and to facilitate the understanding of those skilled in the art. Note that the inventor provides the accompanying drawings and the following description so that those skilled in the art can fully understand the present disclosure, and the subject matter described in the claims is not limited thereby.

[0010] (Embodiment 1) In Embodiment 1, as an example of using the determination method and determination device according to the present disclosure, a determination system for detecting components of light generated in laser processing for overlay welding, acquiring a signal based on the detected components, and determining the processing state will be described.

[0011] 1. Configuration The determination system according to Embodiment 1 will be described with reference to FIG. 1. FIG. 1 is a diagram showing an overview of the determination system 100 according to the present embodiment.

[0012] 1-1. System Overview The determination system 100 includes a laser processing device 30 that performs laser processing for overlay welding, a spectroscopic device 40 that detects components of light, and a determination device 50. The determination device 50 is an example of the determination device according to the present disclosure. The workpiece 70 for overlay welding is made of, for example, metal, and when irradiated with the laser beam 6, thermal radiation light in the near-infrared region due to temperature rise (also referred to as "thermal radiation"), and light emission or plasma emission specific to the metal, which is mainly a visible light component, are generated. In addition, a part of the laser beam 6 that does not contribute to the processing is reflected as return light. Thus, when the laser beam 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 part 27, which is an example of the welded part formed in the workpiece 70.

[0013] The generated light is focused by the laser processing apparatus 30 and transmitted to the spectroscopic apparatus 40 through the optical fiber 13 connecting the laser processing apparatus 30 and the spectroscopic apparatus 40. The light transmitted to the spectroscopic apparatus 40 is split into thermal radiation, visible light, and reflected light, detected by the optical sensor 22 of the spectroscopic apparatus 40, and converted into a signal. When the determination apparatus 50 receives a signal from the spectroscopic apparatus 40, it determines the deviation of the focal position F1 of the laser beam 6 and outputs the determination result.

[0014] The deviation of the focal position F1 is determined by a numerical value including the distance ("-" or "+") in the irradiation direction with respect to a reference value "0" which is the position where the spot diameter of the laser beam 6 is minimized in the vicinity of the surface of the workpiece 70 when irradiating the workpiece 70 with the laser beam 6. The reference position may be any position on the optical path of the laser beam 6. For example, the reference position may be in the vicinity of the surface of the workpiece 70. The reference position may also be the focal position when performing laser processing on a certain workpiece 70 when repeating laser processing on a plurality of workpieces 70. For example, the laser processing apparatus 30 may store the initial focal position and use this as a reference for the deviation of the focal position after the second time.

[0015] 1-2. Configuration of Laser Processing Apparatus FIG. 2 is a diagram illustrating the configuration of the laser processing apparatus 30 of the present embodiment. The laser processing apparatus 30 includes a laser oscillator 1, a laser transmission fiber 2, a lens barrel 3, a collimating lens 4, focusing lenses 5 and 11, a first mirror 7, and a second mirror 8.

[0016] The laser oscillator 1 supplies light for generating, for example, 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 by the laser transmission fiber 2, passes through the collimating lens 4 for obtaining a parallel beam, forms the laser beam 6, and travels straight through the lens barrel 3. The lens barrel 3 constitutes a processing head in the laser processing apparatus 30.

[0017] The laser beam 6 is reflected except for a part that passes through the first mirror 7, and is condensed by the condenser lens 5 and irradiated onto a workpiece 70 fixed by a holding jig 26 on, for example, a scanning table (not shown). Thereby, laser processing for butt welding of the workpiece 70 is performed. Note that the wavelength of the laser beam 6 is not particularly limited to 1070 nm, and it is preferable to use a wavelength with a high absorption rate of the material.

[0018] When the laser beam 6 is irradiated, thermal radiation from the workpiece 70, visible light due to plasma emission, and reflected light of the laser beam 6 are generated in the molten portion 27. These lights pass through the first mirror 7, are reflected by the second mirror 8, are condensed by the condenser lens 11, and then are transmitted through the optical fiber 13 to the spectroscopic device 40. Note that light that partially passes through the second mirror 8 may be detected by a camera or a sensor.

[0019] 1-3. Configuration of Spectroscopic Device FIG. 3 is a diagram illustrating the configuration of the spectroscopic device 40 of the present embodiment. The spectroscopic device 40 includes a collimating lens 15, a third mirror 16, a fourth mirror 17, a fifth mirror 18, condenser lenses 19, 20, 21, an optical sensor 22, a transmission cable 23, and a controller 24 inside a housing 28. The housing 28 prevents stray light from entering the inside from the outside of the spectroscopic device 40 and prevents light leakage from the inside.

[0020] The collimating lens 15 returns the light transmitted through the optical fiber 13 from the laser processing apparatus 30 to parallel light. The third mirror 16 transmits visible light having a wavelength of, for example, 400 nm to 700 nm and reflects other components. The fourth mirror 17 reflects the reflected light of the laser beam 6 having a wavelength of, for example, about 1070 nm and transmits other components. The fifth mirror 18 reflects thermal radiation having a wavelength of, for example, 1300 nm to 1550 nm.

[0021] The light passing through the collimating lens 15 is split into visible light, reflected light, and thermal radiation by the third mirror 16, the fourth mirror 17, and the fifth mirror 18, and is focused by the condenser lenses 19 to 21, respectively. Note that by disposing an arbitrary band-pass filter in the optical path after the third mirror 16, the fourth mirror 17, and the fifth mirror 18, respectively, it may be possible to select the wavelength to be passed.

[0022] The optical sensor 22 includes, for example, optical sensors 22a, 22b, and 22c each having high sensitivity to different wavelengths. The optical sensors 22a, 22b, and 22c detect the visible light, reflected light, and thermal radiation focused by the condenser lenses 19 to 21, respectively, and generate an electrical signal corresponding to the intensity of the detected light. Note that the optical sensor 22 may be constituted by one optical sensor capable of detecting the intensity for each wavelength.

[0023] 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 and comprehensively controls the operation of the entire spectroscopic apparatus 40. The controller 24 includes a CPU and a communication circuit, etc., and transmits the electrical signal received from the optical sensor 22 to the determination device 50. The controller 24 includes, for example, an A / D converter and converts an analog electrical signal into a digital signal (simply referred to as a "signal"). Note that the sampling period when converting to a digital signal is, from the viewpoint of ensuring a sufficient number of samples to capture the characteristics of the processing process and the tendency of the local value of the physical quantity in the determination of the processing state, preferably 1 / 100 or less of the time for performing the output control of the laser beam 6.

[0024] 1-4. Configuration of the determination device FIG. 4 is a block diagram illustrating the configuration of the determination device 50 of the present embodiment. The determination device 50 is constituted by an information processing device such as a computer, for example. The determination device 50 includes a CPU 51 that performs arithmetic processing, a communication circuit 52 for communicating with other devices, and a storage device 53 that stores data and computer programs.

[0025] The CPU 51 is an example of the arithmetic circuit of the determination device in the present embodiment. The CPU 51 realizes a predetermined function including training and execution of the determination model 57 by executing the control program 56 stored in the storage device 53. The determination device 50 realizes the function as the determination device in the present embodiment by the CPU 51 executing the control program 56. Note that the arithmetic circuit configured as the CPU 51 in the present embodiment may be realized by various processors such as an MPU or a GPU, or may be configured by one or a plurality of processors.

[0026] The communication circuit 52 is a communication circuit that communicates in accordance with a standard such as IEEE802.11, 4G, or 5G. The communication circuit 52 may perform wired communication in accordance with a standard such as Ethernet (registered trademark). The communication circuit 52 can be connected to a communication network such as the Internet. Further, the determination device 50 may directly communicate with other devices via the communication circuit 52, or may communicate via an access point. Note that the communication circuit 52 may be configured to be able to communicate with other devices without going through a communication network. For example, the communication circuit 52 may include connection terminals such as a USB (registered trademark) terminal and an HDMI (registered trademark) terminal.

[0027] The storage device 53 is a storage medium that stores computer programs and data necessary to realize the functions of the determination system 100, and stores the control program 56 executed by the CPU 51 and various types of data. The storage device 53 stores the determination model 57 after the construction of the determination model 57. The determination model 57 is constructed based on training data including the feature amount calculated under the situation where the deviation of the focal position F1 of the laser beam 6 has occurred and the deviation of the generated focal position F1. Details of the determination model 57 will be described later.

[0028] The memory device 53 is composed of a magnetic memory device such as a hard disk drive (HDD), an optical memory device such as an optical disk drive, or a semiconductor memory device such as an SSD. The memory device 53 may include a temporary storage element composed of a RAM such as DRAM or SRAM, and may function as an internal memory of the CPU 51.

[0029] 2. Operation In the determination system 100 configured as described above, for example, as shown in FIG. 1, the spectroscopic device 40 detects, by means of the optical sensor 22, the thermal radiation, visible light, and reflected light generated in the melting portion 27 by the irradiation of the laser light 6. The spectroscopic device 40 transmits a signal corresponding to the detected intensities of the thermal radiation, visible light, and reflected light to the determination device 50. The operation of the determination device 50 in this system 100 will be described below.

[0030] 2-1. Determination Process Hereinafter, in the determination device 50, a determination process for determining the deviation of the focal position F1 as the processing state will be described with reference to FIGS. 5 to 8.

[0031] FIG. 5 is a flowchart illustrating the determination process in the determination device 50 of the present embodiment. Each process shown in this flowchart is executed, for example, by the CPU 51 of the determination device 50. This flowchart is started, for example, when a predetermined operation for starting the determination process is input by a user or the like of the determination system 100 from an input device connected via the communication circuit 52.

[0032] First, the CPU 51 acquires, via the communication circuit 52, signals corresponding to the thermal radiation, visible light, and reflected light detected by the optical sensor 22 of the spectroscopic device 40 (S1).

[0033] FIG. 6 is a diagram for explaining the signals acquired by the determination device 50. (A), (B), and (C) in FIG. 6 show signal waveforms corresponding to the intensities of thermal radiation, visible light, and reflected light, respectively. (D) in FIG. 6 shows the output of the laser beam 6 irradiated on the workpiece 70. Each of the signals in (A) to (C) of FIG. 6 corresponds to the thermal radiation, visible light, and reflected light generated by the laser output. In (A) to (D) of FIG. 6, the horizontal axis represents time, and the vertical axis represents signal intensity ((A) to (C) of FIG. 6) or laser output ((D) of FIG. 6). Also, the time T1 corresponds to the time interval of one pulse of the laser beam 6, and the time T2 represents the time interval of the peak output excluding the rise and fall of the laser output.

[0034] Here, in the laser processing apparatus 30 of the present embodiment, welding for each workpiece 70 is performed at the time T1 corresponding to one pulse of the laser beam 6. In step S1 of FIG. 5, as shown in (A) to (C) of FIG. 6, the CPU 51 acquires signals indicating changes in thermal radiation, visible light, and reflected light at the time T1 corresponding to the welding time for each workpiece 70. However, the intensities of thermal radiation, visible light, and reflected light are affected by the residual heat after processing, and the end of the signal waveform may extend temporally from the laser output. Even in this case, by extracting a predetermined section T3 described later, it is possible to determine the deviation of the focal position without being affected by the residual heat.

[0035] Next, the CPU 51 calculates a feature amount to be input to the determination model 57 from the acquired signals (S2).

[0036] FIG. 7 is a diagram for explaining the process (S2) of calculating the feature amount in the determination device 50. (A) in FIG. 7 shows the time change of the signal intensity of the signal corresponding to thermal radiation, visible light, or reflected light on the same vertical and horizontal axes as (A) to (C) of FIG. 6. (B) in FIG. 7 shows the signal waveform obtained by applying a smoothing process to the signal in (A) of FIG. 7. In step S2 of FIG. 5, the CPU 51 applies a smoothing filter to the signals of each component as shown in (A) of FIG. 7 acquired in step S1 to perform a smoothing process, thereby generating a signal waveform as shown in (B) of FIG. 7.

[0037] (C) in FIG. 7 shows a predetermined section T3 among time T1, T2, and time T1 in the signal waveform of (B) in FIG. 7. In step S2, the CPU 51 sets a straight line Ls that approximates the signal waveform in a predetermined section T3 as shown in (D) of FIG. 7, and calculates the slope of the straight line Ls as a feature amount. The section T3 is preset as a section of 1 to 3 milliseconds from the center 60 of the time T2 corresponding to the peak output of the laser beam 6 among the times T1 of one pulse of the laser beam 6. In the example of (D) in FIG. 7, as a feature amount of the slope, the slope of the straight line Ls determined by two points of the signal waveform after smoothing passing through both ends of the section T3 is calculated.

[0038] In the present embodiment, in step S2 of FIG. 5, the CPU 51 calculates, as feature amounts, the slopes of the signal waveforms corresponding to thermal radiation, visible light, and reflected light. In particular, thermal radiation and visible light are likely to reflect changes in the molten state of the material of the workpiece 70, and by using the slopes of the signal waveforms for these, it is possible to accurately determine the deviation of the focal position F1.

[0039] Also, in the present embodiment, in step S2 of FIG. 5, the CPU 51 further calculates, as a feature amount, the signal intensity obtained by performing preprocessing such as normalization on the signals of thermal radiation, visible light, and reflected light. The feature amount of the signal intensity is input to the determination model 57, for example, as the amplitude of the signal waveform for each sampling period in A / D conversion.

[0040] Also, in step S2 of the present embodiment, the CPU 51 further calculates, as a feature amount, the integral value of the signal intensity for the signal corresponding to the reflected light. The CPU 51 calculates, for example, the integral value of the signal intensity at time T1. The integral value of the signal intensity may be calculated by integrating the signal intensity limited to a time T2 shorter than time T1, section T3, or other time sections according to the signal waveform. The reflected light has less signal intensity variation as in the example of (C) in FIG. 6 compared to other components, and is considered to most reflect the output waveform of the laser beam 6. Thereby, by using the integral value of the signal intensity of the reflected light, it is possible to accurately reflect and determine the change in the emission energy due to the deviation of the focal position F1.

[0041] After calculating the feature amount (S2), the CPU 51 performs a process (S3) of inputting the feature amount into the determination model 57 to determine the deviation of the focal position F1. In the present embodiment, in the process (S3) of the determination model, the CPU 51 determines, as the deviation of the focal position F1, a numerical value indicating the relative position of the focal position F1 with respect to the reference position.

[0042] FIG. 8 is a diagram for explaining the process (S3) of the determination model. FIG. 8 shows the signal waveform after smoothing (FIG. 8(A)) when the focal position F1 of the laser beam 6 is on the plus (+) side, near the reference position of "0", or on the minus (-) side, and the positional relationship between the focal position F1 of the laser beam 6 and the workpiece 70 (FIG. 8(B)). In FIG. 8, the deviation of the focal position F1 is represented by the same coordinate axes as in FIG. 1.

[0043] The process (S3) of the determination model is performed by the determination model 57 learned based on the correspondence between the signal waveform and the focal position F1 as shown in FIG. 8. Hereinafter, the findings obtained by the inventors of the technology in the present disclosure regarding the correspondence between the signal waveform and the focal position F1 will be described with reference to FIG. 8.

[0044] When the focal position F1 is near the reference "0", that is, in the just-focus state where the spot diameter of the laser beam 6 is the smallest near the surface of the workpiece 70, the slope of the signal waveform is close to "0". When the focal position F1 deviates in the positive direction, while the signal intensity increases compared to the just-focus state, the slope becomes smaller. When the focal position F1 deviates in the negative direction, the signal intensity increases compared to the just-focus state, and the slope also becomes larger. A small slope means a negative slope (the signal intensity decreases with time). A large slope means a positive slope (the signal intensity increases with time).

[0045] As a factor that the signal intensity increases when the focal position F1 shifts, it is conceivable that the irradiation area of the laser beam 6 on the surface of the workpiece 70 increases, and the light emission area in the melting part 27 increases. Regarding the slope of the signal waveform, at the start of the welding process, the surface of the workpiece 70 melts and evaporates due to the irradiation of the laser beam 6, and thus a cavity (keyhole) is formed on the surface. The formation of the keyhole requires heat input by the laser beam 6. However, when the focal position F1 shifts, the heat input amount becomes high at a timing different from the just-focused state, so that heat radiation, visible light, etc. are particularly likely to be generated from the melting part 27, and it is assumed that the slope of the signal waveform changes. Furthermore, when the focal position F1 shifts in the positive direction, the total amount of heat irradiated on the surface and inside of the workpiece 70 is small, and since the focal position F1 exists outside the workpiece 70, heat easily escapes. Conversely, when the focal position F1 shifts in the negative direction, the total amount of heat irradiated on the surface and inside of the workpiece 70 is large, and since the focal position F1 exists inside the workpiece 70, heat is less likely to escape. Therefore, it is considered that when the focal position F1 shifts in the positive direction, the slope becomes small, and when the focal position F1 shifts in the negative direction, the slope becomes large.

[0046] Based on the above findings, the inventor of the present invention speculated that it is possible to predict the deviation of the focal position F1 using feature quantities such as the slope and signal intensity of the signal waveform from a signal corresponding to at least one of heat radiation, visible light, and reflected light. Therefore, as will be described later, the inventor constructed a determination model 57 using these feature quantities and the deviation of the focal position F1 as training data, and performed a determination process by the determination model 57. According to the determination model 57 constructed in this way, when a feature quantity based on a signal is input, a deviation including the distance of the focal position F1 is output (S3).

[0047] Returning to FIG. 5, the CPU 51 outputs the determination result of the deviation of the focal position F1 determined by the process of the determination model (S3) through the communication circuit 52 (S4). The determination result can be received and displayed by, for example, an external information processing device or a display device. Further, the determination device 50 may include a display device (for example, a display) capable of communicating with the CPU 51, and the determination result may be displayed on the display device.

[0048] After that, the CPU 51 ends the flowchart of FIG. 5. The flowchart of FIG. 5 is repeatedly executed, for example, each time welding is performed on the workpiece 70.

[0049] According to the above determination process, the determination device 50 of the present embodiment acquires the signal generated by the optical sensor 22 of the spectroscopic device 40 (S1), calculates the feature amount from the signal (S2), and determines the deviation of the focal position F1 by the determination model 57 based on the feature amount (S3). Thereby, the determination device 50 can accurately determine the deviation of the focal position F1 of the laser beam 6 as the processing state in the laser processing for overlap welding.

[0050] In step S2 of FIG. 5, as the feature amount, the slope of the signal waveform and / or the integral value of the signal intensity may be calculated for all of the thermal radiation, visible light, and reflected light, or may be calculated for only one of them.

[0051] 2-2. Training process Hereinafter, the training process for constructing the determination model 57 will be described with reference to FIGS. 9 and 10.

[0052] FIG. 9 is a flowchart illustrating the training process of the determination model 57. Each process of this flowchart is executed, for example, by the CPU 51 of the determination device 50.

[0053] First, the CPU 51 acquires the training data stored in advance in the storage device 53, for example (S11).

[0054] FIG. 10 is a diagram for explaining the training data D1 of the determination model 57. The training data D1 is data that associates feature amounts such as, for example, the slopes of the signal waveforms of thermal radiation, visible light, and reflected light, the integrated value of the signal intensity of the reflected light, and the signal intensities of the thermal radiation, visible light, and reflected light (not shown) with the deviation of the focal position F1. The training data D1 is constructed by calculating feature amounts from signals based on the thermal radiation, visible light, and reflected light actually detected under a plurality of conditions in which the deviation of the focal position F1 changes, and associating and recording them with the deviation of the focal position F1 at that time.

[0055] Returning to FIG. 9, when the CPU 51 acquires the training data D1 (S1), it performs machine learning using the training data D1 to generate the determination model 57 (S2). The determination model 57 is generated as a regression model based on, for example, 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.

[0056] According to the above training process, the determination model 57 can be generated as a learned model for determining the deviation of the focal position F1 from the feature amounts based on the signals corresponding to the thermal radiation, visible light, and reflected light detected in laser processing.

[0057] Note that the training process of the determination model 57 may be executed in an information processing device different from the determination device 50. The determination device 50 may acquire a constructed determination model by the communication circuit 52 via, for example, a communication network.

[0058] 3. Effects, etc. As described above, in the present embodiment, the determination process (S1 to S4) provides a method for determining the processing state in laser processing for overlap welding. This method uses the optical sensor 22 to detect at least one of the thermal radiation (thermal radiation light), 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 when the laser beam 6 irradiates the workpiece 70. A step of detecting; a step (S1) of acquiring a signal indicating a change in at least one of thermal radiation, visible light, and reflected light in a time T1 (time interval) corresponding to the welding time for each workpiece 70; a step of calculating a feature amount including the slope of a straight line Ls approximating the signal waveform in a predetermined section T3 of the time T1 (S2); a step (S3) of inputting the calculated feature amount into a determination model 57 for determining the processing state and determining a deviation including the distance of the focal position F1 in the irradiation direction of the laser beam 6 as the processing state; and a step (S4) of outputting the determined deviation of the focal position F1 as a determination result. The determination model 57 is constructed based on training data D1 including the feature amount calculated in the situation where the deviation of the focal position F1 occurs and the deviation of the generated focal position F1 associated with each other.

[0059] 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 the irradiation of the laser beam 6 is acquired (S1), a feature amount such as the slope of the straight line Ls approximating the signal waveform is calculated (S2), and determination is performed by the determination model 57 (S3). Thereby, the processing state can be determined in detail by the determination model 57 constructed using the training data D1 that relates the feature amount such as the slope of the signal waveform to the deviation including the distance of the focal position F1 of the laser beam 6 as the processing state.

[0060] In the present embodiment, the determination model 57 includes a learned model generated by machine learning using training data D1 that associates a feature amount calculated from a signal based on at least one of thermal radiation, visible light, and reflected light detected by performing laser processing under each of a plurality of conditions in which the processing state changes, and the deviation of the focal position F1 under each condition (S11 to S12). Thereby, a determination model 57 for determining the deviation of the focal position F1 as the processing state is obtained from the feature amount based on at least one of the detected thermal radiation, visible light, and reflected light.

[0061] In the present embodiment, the deviation F1 of the focal position is determined based on a preset position along the overlapping direction in the overlapping welding. The deviation of the focal position F1 includes a numerical value indicating the relative position of the focal position with respect to the reference position. Thereby, the processing state in the laser processing can be determined in detail, including how much the focal position F1 is deviated far or near in the irradiation direction of the laser beam 6.

[0062] In the present embodiment, the step (S2) of calculating the feature amount includes smoothing the signal waveform of the signal before calculating the feature amount. Thereby, in a signal waveform in which the signal intensity fluctuates finely (see FIG. 6), it is possible to easily calculate the feature amount of the slope.

[0063] In the present embodiment, the feature amount includes the signal intensity of the signal. Thereby, for example, the determination of the processing state by the determination model 57 can be performed using the information of the signal waveform according to the temporal change of the signal intensity as it is.

[0064] In the present embodiment, the feature amount includes the integrated value of the signal intensity of the signal. Thereby, it is possible to easily determine the deviation of the focal position F1 by reflecting the tendency that the signal intensity increases as the deviation of the focal position F1 continues over time while the laser output continues.

[0065] In the determination system 100 of this embodiment, the determination device 50 is an example of a device for determining the processing state in laser processing for overlap welding. The determination device 50 includes a CPU 51 as an example of an arithmetic circuit and a communication circuit 52. The communication circuit 52 receives a signal generated by detecting at least one of thermal radiation (thermal radiation light), visible light, and reflected light that occurs in the molten part 27 (an example of a welded part) formed on the surface of the workpiece 70 when the laser beam 6 irradiates the workpiece 70, by the optical sensor 22. The signal is a signal indicating at least one change in thermal radiation, visible light, and reflected light at time T1, which is an example of a time interval corresponding to the welding time for each workpiece 70. The CPU 51 acquires the signal through the communication circuit 52 (S1), calculates a feature amount including the slope of a straight line Ls that approximates the signal waveform in a predetermined section T3 within the time T1 (S2), inputs the calculated feature amount into a determination model 57 for determining the processing state, and determines the deviation including the distance of the focal position F1 in the irradiation direction of the laser beam 6 as the processing state (S3). Then, the CPU 51 outputs the determined deviation of the focal position F1 as a determination result through the communication circuit 52 (S4). The determination model 57 is constructed based on training data D1 that associates the feature amount calculated under the situation where the deviation of the focal position F1 occurs with the generated deviation of the focal position F1.

[0066] According to the above determination device 50, the above-described determination method can be executed to determine in detail the processing state in laser processing for overlap welding.

[0067] (Other embodiments) As described above, as an exemplification of the technology disclosed in this application, the above embodiments have been described. However, the technology in this disclosure is not limited to this, and is also applicable to embodiments with appropriate changes, replacements, additions, omissions, etc. Further, it is also possible to combine the components described in the above embodiments to form a new embodiment.

[0068] In the above-described Embodiment 1, the determination device 50 calculated, as feature amounts, in addition to the slopes of the signal waveforms of signals corresponding to thermal radiation and visible light, the signal intensities of thermal radiation, visible light, and reflected light, and the integrated value of the signal intensity of the reflected light (S2). In the present embodiment, the feature amounts are not particularly limited to these, and for example, only the slope of the signal waveform may be used, or neither the signal intensity nor the integrated value may be included. Further, only the signal intensity of at least one of thermal radiation, visible light, and reflected light may be used as a feature amount.

[0069] In the above-described Embodiment 1, when calculating the feature amounts (S2), the determination device 50 smoothed the signal waveform and then calculated the feature amount of the slope. In the present embodiment, without performing smoothing, for example, in the signal waveform before smoothing, the slope of the straight line determined by two points at both ends of the section T3 may be calculated.

[0070] In the above-described Embodiment 1, when calculating the feature amounts (S2), as the slope of the signal waveform, the determination device 50 calculated the slope of the straight line Ls determined by two points of the signal waveform passing through both ends of the section T3 as shown in (D) of FIG. 7. In the present embodiment, the slope of the signal waveform may be calculated, for example, by averaging the slopes of a plurality of straight lines approximating the signal waveform in each section obtained by further dividing the section T3.

[0071] In the above-described Embodiment 1, the determination device 50 calculated the slopes of the signal waveforms of thermal radiation and visible light as feature amounts (S2). In the present embodiment, the feature amount of the slope may be calculated based on either thermal radiation or visible light. For example, depending on the material of the workpiece 70, thermal radiation may be used when the material is an aluminum material, and visible light may be used when the material is an iron-based material, but the present invention is not limited thereto, and it is preferable to select according to the absorption rate of the material with respect to the laser wavelength.

[0072] According to the determination method and the determination device in the present disclosure, a deviation including the distance of the focal position in the irradiation direction of the laser light is determined. Thereby, the processing state in the laser processing for overlap welding can be determined in detail.

[0073] The present disclosure is not limited to the above-described 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.

Industrial Applicability

[0074] The present disclosure is applicable to a processing state determination system in laser processing for butt welding, and particularly applicable to a method and apparatus for determining the deviation of the focal position of a laser beam.

Explanation of Signs

[0075] 1 Laser oscillator 2 Laser transmission fiber 3 Lens barrel 4 Collimating lens 5, 11 Condensing lenses 6 Laser beam 7 First mirror 8 Second mirror 13 Optical fiber 15 Collimating lens 16 Third mirror 17 Fourth mirror 18 Fifth mirror 19, 20, 21 Condensing lenses 22 Optical sensor 23 Transmission cable 24 Controller 26 Clamping jig 27 Melting part 30 Laser processing apparatus 40 Spectroscopic apparatus 50 Determination apparatus 51 CPU 52 Communication circuit 53 Storage device 56 Control program 57 Determination model 70 Workpiece F1 Focal position D1 Training data 100 Determination system

Claims

1. A method for determining a processing state in laser processing for butt welding, comprising: using an optical sensor to detect at least one of thermal radiation light, visible light, and reflected light generated at a welded portion formed on the surface of the workpiece by irradiating the workpiece with laser light; obtaining from the optical sensor a signal indicating a change in at least one of the thermal radiation light, the visible light, and the reflected light in a time interval corresponding to the welding time for each workpiece; calculating a feature amount including the slope of a straight line approximating the signal waveform of the signal in a predetermined section of the time interval; inputting the calculated feature amount into a determination model for determining the processing state, and determining, as the processing state, a deviation including the distance of the focal position in the irradiation direction of the laser light; outputting the determined deviation of the focal position as a determination result; including: The determination model is constructed based on training data including the feature amount calculated under the situation where the deviation of the focal position occurs and the deviation of the generated focal position associated therewith. Determination method.

2. The determination model includes a trained model generated by machine learning using training data associating a feature amount calculated from a signal based on at least one of the thermal radiation light, the visible light, and the reflected light detected by performing the laser processing under each of a plurality of conditions in which the processing state changes, and the deviation of the focal position under each of the conditions. The determination method according to claim 1.

3. The deviation of the focal position is determined along the butt-welding direction in the butt welding with reference to a preset position, The deviation of the focal position includes a numerical value indicating the relative position of the focal position with respect to the reference position. The determination method according to claim 2.

4. The step of calculating the feature amount includes smoothing the signal waveform of the signal before calculating the feature amount. The determination method according to any one of claims 1 to 3.

5. The feature amount includes the signal intensity of the signal. The determination method according to any one of claims 1 to 4.

6. The feature amount includes an integral value of the signal intensity of the signal. The determination method according to any one of claims 1 to 5.

7. A determination device for a processing state in laser processing for butt welding, comprising: an arithmetic circuit; A communication circuit that receives a signal generated by detecting at least one of thermal radiation light, visible light, and reflected light generated in a welded portion formed on the surface of the workpiece when the laser light irradiates the workpiece. Comprising The signal is a signal indicating at least one change among the thermal radiation light, the visible light, and the reflected light in a time interval corresponding to the welding time for each workpiece. The arithmetic circuit Acquires the signal by the communication circuit. Calculates a feature amount including the slope of a straight line approximating the signal waveform of the signal in a predetermined section of the time interval. Inputs the calculated feature amount into a determination model for determining the processing state, and determines a deviation including the distance of the focal position in the irradiation direction of the laser light as the processing state. Outputs the determined deviation of the focal position as a determination result by the communication circuit. The determination model is constructed based on training data including the feature amount calculated under the situation where the deviation of the focal position occurs and the deviation of the generated focal position associated with each other. Determination device.

8. The determination model includes a learned model generated by machine learning using training data associating a feature amount calculated from a signal based on at least one of the thermal radiation light, the visible light, and the reflected light detected by performing the laser processing under each of a plurality of conditions in which the processing state changes, and the deviation of the focal position under each condition. The determination device according to claim 7.

9. The deviation of the focal position is determined with reference to a preset position along the overlapping direction in the overlapping welding. The deviation of the focal position includes a numerical value indicating the relative position of the focal position with respect to the reference position. The determination device according to claim 8.

10. Before calculating the feature amount, the arithmetic circuit performs a process of smoothing the signal waveform of the signal. The determination device according to any one of claims 7 to 9.

11. The feature amount includes the signal intensity of the signal. The determination device according to any one of claims 7 to 10.

12. The feature amount includes an integrated value of the signal intensity of the signal. The determination device according to any one of claims 7 to 11.

Images