Laser processing device, control device, laser processing system, and laser processing method

Through beam characteristic calculation, temperature estimation and imaging performance estimation, the optical component temperature and imaging performance of the laser processing device are corrected in real time, solving the problem of imaging performance deterioration caused by temperature changes of optical components, and achieving stability and high efficiency of laser processing.

CN118984752APending Publication Date: 2024-11-19MITSUBISHI ELECTRIC CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202280094126.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2022-04-12
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

During the processing process, the thermal lens effect caused by the temperature changes of optical components cannot be sufficiently suppressed and the deterioration of laser imaging performance is affected, which affects the processing quality.

Method used

The methods of beam characteristic calculation, temperature estimation, thermal lens estimation and imaging performance estimation are used to monitor and correct the temperature and imaging performance of optical components in real time, and the processing parameters are adjusted by calculating the correction amount to ensure the stability of imaging performance.

Benefits of technology

It effectively suppresses the deterioration of laser processing quality, improves processing accuracy and stability, ensures constant imaging performance, and improves processing effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118984752A_ABST
    Figure CN118984752A_ABST
Patent Text Reader

Abstract

A laser processing device (100) is provided with: a beam characteristic calculation unit (14) that calculates beam characteristics of laser light irradiated to an optical member (30) disposed on a processing head (3); an optical member temperature estimation unit (15) that estimates the estimated temperature of the optical member on the basis of temperature information (P5), which is information on the temperature measured by a temperature sensor (7) disposed in the processing head, and the luminous flux characteristics; a thermal lens estimation unit (16) that estimates the thermal lens amount of the optical member on the basis of the estimated temperature; an imaging performance change estimation unit (17) that estimates, on the basis of the thermal lens amount, an estimated imaging performance change amount, which is the amount of change in imaging performance of an imaging optical system of the machining head from the start of machining; a correction amount calculation unit (22) that calculates a correction amount for the machining parameter (P1) on the basis of the estimated imaging performance change amount; and a control unit (11) that controls laser processing using the laser light, and that changes the processing parameter on the basis of the correction amount during the laser processing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a laser processing device, a control device, a laser processing system and a laser processing method for performing laser processing. Background Art

[0002] A laser processing device that performs laser processing of a workpiece by irradiating a laser to the workpiece focuses the laser at a specific position through an optical component contained in a processing head, and irradiates the focused laser to the workpiece. In the laser processing device as described above, the optical component absorbs the laser, thereby generating a thermal lens effect in which the refractive index of the optical component changes. Therefore, in the laser processing device, the imaging performance of the laser changes, and although the processing is good at the beginning, sometimes poor processing occurs as the processing proceeds.

[0003] The laser processing device described in Patent Document 1 adjusts the focal position of the laser beam by moving the lens in the optical axis direction by a drive motor according to the lens temperature detected by a temperature sensor provided on the lens.

[0004] Patent Document 1: Japanese Patent Application Publication No. 2000-94173 Summary of the invention

[0005] However, the technique of Patent Document 1 mentioned above only moves the lens in the optical axis direction according to the lens temperature, and therefore cannot take into account changes in the imaging performance of the imaging optical system, resulting in insufficient suppression of degradation in laser processing quality.

[0006] The present invention has been made in view of the above-mentioned circumstances, and an object of the present invention is to obtain a laser processing apparatus that can sufficiently suppress degradation of laser processing quality.

[0007] In order to solve the above-mentioned problems and achieve the purpose, the laser processing device of the present invention has: a beam characteristic calculation unit that calculates the beam characteristic of the laser beam irradiated to the optical component arranged in the processing head; and a temperature estimation unit that estimates the estimated temperature of the optical component based on the temperature information measured by the temperature sensor arranged in the processing head, that is, the temperature information and the beam characteristic. In addition, the laser processing device of the present invention has: a thermal lens estimation unit that estimates the thermal lens amount of the optical component based on the estimated temperature; and an imaging performance change estimation unit that estimates the change amount of the imaging performance of the imaging optical system of the processing head from before the start of the processing, that is, the estimated imaging performance change amount, based on the thermal lens amount. In addition, the laser processing device of the present invention has: a correction amount calculation unit that calculates the correction amount of the processing parameter based on the estimated imaging performance change amount; and a control unit that controls the laser processing using the laser and changes the processing parameter based on the correction amount during the laser processing.

[0008] Effects of the Invention

[0009] The laser processing apparatus according to the present invention has an effect of being able to sufficiently suppress deterioration in laser processing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a diagram showing the structure of the laser processing device involved in Embodiment 1.

[0011] Figure 2 This is a diagram for explaining the arrangement structure of optical components included in the processing head of the laser processing device involved in the first embodiment.

[0012] Figure 3 This is a diagram for explaining the thermal lens effect generated in the laser processing device according to the first embodiment.

[0013] Figure 4 This is a block diagram showing the functional structure of the laser processing device involved in Embodiment 1.

[0014] Figure 5 This is a flowchart showing a processing procedure of processing control performed by a processing control unit of the laser processing device according to the first embodiment.

[0015] Figure 6 This is a block diagram showing the functional structure of the laser processing device involved in embodiment 2.

[0016] Figure 7 This is a block diagram showing the functional structure of the laser processing device involved in Embodiment 3.

[0017] Figure 8 This is a block diagram showing the functional structure of the laser processing device involved in the fourth embodiment.

[0018] Fig. 9 This is a diagram showing a structural example of a neural network model involved in Implementation Example 4.

[0019] Fig.10 This is a diagram showing a configuration example of a processing circuit when the processing circuit included in the process control unit according to the first to fourth embodiments is realized by a processor and a memory.

[0020] Fig.11 This is a diagram showing an example of a processing circuit in the case where the processing circuit included in the process control section according to the first to fourth embodiments is configured by dedicated hardware. DETAILED DESCRIPTION

[0021] Hereinafter, a laser processing device, a control device, a laser processing system, and a laser processing method according to embodiments of the present invention will be described in detail with reference to the drawings.

[0022] Implementation method 1.

[0023] Figure 1 : is a diagram showing the structure of the laser processing device involved in the first embodiment. In the following, two axes in a plane parallel to the upper surface of the plate-shaped workpiece, that is, the workpiece W, and two axes orthogonal to each other are set as the X axis and the Y axis. In addition, the axis orthogonal to the X axis and the Y axis is set as the Z axis. For example, the XY plane is a horizontal plane, and the Z axis direction is a direction parallel to the vertical direction. In addition, the workpiece W is not limited to a plate shape.

[0024] The laser processing device 100 irradiates a workpiece W with laser light L as a laser beam to perform laser processing on the workpiece W. The laser processing device 100 focuses the laser light L using optical components included in the processing head 3 and irradiates the focused laser light L on the workpiece W, thereby processing the workpiece W.

[0025] The laser processing device 100 includes a laser oscillator 1, a control unit 11, an optical fiber 2, and a processing head 3. The processing head 3 includes a collimating lens 4, an imaging optical system 5, two optical component holders 6, two temperature sensors 7, a protective glass 8, a processing nozzle 9, and drive units 10A to 10C as motor drive devices.

[0026] The control unit 11 is connected to the laser oscillator 1 and the processing head 3 to control the laser oscillator 1 and the processing head 3. The control unit 11 is arranged in a processing control unit 102 (in Figure 1 (not shown in the figure) The laser oscillator 1 oscillates laser light L. The optical fiber 2 transmits the laser light L oscillated by the laser oscillator 1 to the processing head 3.

[0027] In the processing head 3, the optical component holder 6 disposed on the upper side supports the collimating lens 4, and the optical component holder 6 disposed on the lower side supports the imaging optical system 5. A temperature sensor 7 is disposed on each of the optical component holders 6.

[0028] The collimator lens 4 sets the laser light L as parallel light and transmits it to the imaging optical system 5. The imaging optical system 5 images the laser light L at a specific position. The laser light L after passing through the imaging optical system 5 is transmitted to the processing nozzle 9 via the protective glass 8. The protective glass 8 protects the components and the like arranged in the processing head 3 from the splashes during laser processing.

[0029] The processing nozzle 9 irradiates the laser light L after passing through the protective glass 8 to the irradiation position on the workpiece W. Processing gas is supplied to the inside of the processing head 3. When the processing head 3 irradiates the laser light L to the workpiece W, the processing gas is ejected to the workpiece W. The processing nozzle 9 has an opening in the optical path of the laser light L between the imaging optical system 5 and the workpiece W, and the laser light L and the processing gas pass through the opening.

[0030] The laser processing device 100 is provided with a Z-axis motor (not shown) for moving the processing head 3 in the Z-axis direction and a driving unit 10A for driving the Z-axis motor. The Z-axis motor is connected to an axis (axis extending in the Z-axis direction) on which the processing head 3 is provided, and moves the processing head 3 in a direction parallel to the Z-axis direction along the Z-axis.

[0031] In addition, the laser processing device 100 is provided with an X-axis motor (not shown) and a Y-axis motor (not shown) for moving a processing table (not shown) on which a workpiece W is placed within an XY plane, a driving unit (not shown) for driving the X-axis motor, and a driving unit (not shown) for driving the Y-axis motor. The X-axis motor is connected to a shaft extending in the X-axis direction, and the Y-axis motor is connected to a shaft extending in the Y-axis direction. The X-axis motor and the Y-axis motor move the processing table within the XY plane along the X-axis and the Y-axis.

[0032] The control unit 11 controls the laser oscillator 1, the processing head 3, the drive units 10A to 10C, etc. based on numerical parameters related to laser processing, i.e., processing parameters, to perform processing. For example, the control unit 11 controls the drive units 10A to 10C, and the drive units 10A to 10C drive the motors according to the control of the control unit 11. The drive unit 10A moves along with the movement of the motor to change the relative position of the processing head 3 and the workpiece W. Figure 1 , the figure shows a state where the relative position of the machining head 3 and the workpiece W is changed by the driving unit 10A moving the machining head 3 .

[0033] The driving units 10B and 10C change the positional relationship between the imaging position of the imaging optical system 5 of the laser L and the workpiece W. The driving unit 10B is a driving unit for the collimating lens 4, and changes the position of the collimating lens 4 to change the imaging diameter of the imaging optical system 5. The driving unit 10C is a driving unit for the imaging optical system 5, and changes the position of the imaging optical system 5 to change the imaging position of the imaging optical system 5.

[0034] The type of laser oscillator 1 is not limited. An example of the laser oscillator 1 is a fiber laser oscillator that transmits the laser light L through the optical fiber 2. The laser oscillator 1 may also be a direct diode laser, a carbon dioxide laser, a copper vapor laser, various ion lasers, or a solid laser using a YAG (Yttrium Aluminum Garnet) crystal or the like as an excitation medium. In addition, the laser processing device 100 may also include a wavelength conversion unit that converts the wavelength of the laser light L oscillated by the laser oscillator 1.

[0035] In addition, the collimating lens 4 may be one piece or multiple pieces. In addition, the imaging optical system 5 may be one piece or multiple pieces. In addition, the optical system arranged in the processing head 3 may be a zoom optical system that displaces the position of the optical system, thereby changing the imaging diameter of the imaging point. In addition, the optical system arranged in the processing head 3 may be an optical system that displaces the imaging position by adjusting the divergence angle incident on the imaging optical system 5 by displacing the collimating lens 4 by the driving unit. In addition, the imaging position changed by the driving unit 10C may be at the beam waist position of the optical system, or may be a position deviated from the beam waist position.

[0036] The laser processing apparatus 100 may change the relationship between the position of the image forming point of the laser light L and the position of the workpiece W in the height direction, instead of changing the relationship between the position of the processing nozzle 9 in the height direction and the position of the workpiece W in the height direction. In this case, the control unit 11 controls the drive unit 10C, and the drive unit 10C changes the position of the image forming optical system 5 in the height direction.

[0037] In addition, in the processing head 3, a driving unit other than the driving units 10B and 10C may drive other optical components other than the imaging optical system 5. The optical components driven by the processing head 3 may be one or more. The optical components in the first embodiment are the collimating lens 4, the imaging optical system 5, and the protective glass 8, but optical components such as a reflector may also be arranged in the processing head 3.

[0038] According to the above configuration, the laser light L emitted from the optical fiber 2 passes through the collimator lens 4 , is imaged by the image forming optical system 5 , passes through the protective glass 8 , and is irradiated onto the workpiece W as the object to be processed.

[0039] Here, the arrangement structure of the optical components included in the processing head 3 will be described. Figure 2 This is a diagram for explaining the configuration structure of optical components included in the processing head of the laser processing device according to Embodiment 1. Here, the configuration structure of the collimating lens 4 is explained, but the configuration structure of the imaging optical system 5 is also the same as that of the collimating lens 4 .

[0040] like Figure 2 As shown, the collimating lens 4 and other optical components are held by an optical component holder 6 such as a lens holder as an example of a holding portion. The holding portion is composed of a component that holds the optical component, such as the optical component holder 6 that holds the collimating lens 4 and other lenses, or a reflector holder (not shown) that holds a reflector (not shown).

[0041] In addition, a temperature sensor 7 is disposed on the optical component holder 6. Examples of the temperature sensor 7 are a thermocouple and a thermistor. Figure 2 As shown, a water channel 12 for cooling the optical component holder 6 may be provided. When the optical component holder 6 has the water channel 12, the optical component is cooled by flowing cooling water in the water channel 12. In addition, the water channel 12 may be provided in the optical component holder 6 that holds the imaging optical system 5.

[0042] Next, a description will be given of a positional deviation of an imaging point due to a thermal lens effect, which is one of the factors causing changes in imaging performance during laser processing. Figure 3 1 is a diagram for explaining the thermal lens effect generated in the laser processing device involved in the first embodiment. Figure 3 In FIG. 1 , the imaging point position D1 at the start of processing is shown on the left, and the imaging point position D2 after the start of processing is shown on the right.

[0043] In the laser processing device 100, in a transmission optical system such as a lens or a reflection optical system such as a reflector, the glass material or coating of the optical component absorbs the laser light L oscillated by the laser oscillator 1. As a result, the refractive index (distribution of the refractive index) of the optical component changes in the laser processing device 100, and a thermal lens effect occurs. In addition, the time to form a temperature distribution in the optical component varies depending on the material of the optical component and the diameter of the irradiated beam.

[0044] like Figure 3 As shown, in the laser processing device 100, the imaging position of the laser light L at the imaging point may change at the start of processing and after the start of processing. Figure 3 As shown on the left side of FIG. 1 , at the beginning of the processing, the laser processing device 100 has an imaging point located on the surface of the workpiece W, and performs good processing. However, as the processing progresses, the laser processing device 100 Figure 3 As shown on the right side of , sometimes the imaging position changes and the imaging point moves from the surface of the workpiece W toward the processing head 3, thereby causing processing defects.

[0045] The condition for good processing is not limited to the case where the imaging point is on the workpiece W. The imaging point may be located on the processing head 3 side of the workpiece W, or the imaging point may be located on the depth direction side of the workpiece W, which may also be good processing.

[0046] In addition, due to the thermal lens effect, not only the imaging position changes, but also the imaging magnification, beam waist position, aberrations, etc. may be generated, and the imaging performance of the entire processing optical system is deteriorated.

[0047] The laser processing device 100 of the first embodiment accurately estimates the temperature of the optical component by taking into account the temperature sensor 7 included in the processing head 3 even when the thermal lens effect occurs. Furthermore, the laser processing device 100 accurately estimates the change in imaging performance from before the start of processing (hereinafter referred to as imaging performance change amount) based on the estimated temperature of the optical component, determines the correction amount of the processing parameter corresponding to the imaging performance change amount, and corrects the processing parameter. Examples of the processing parameters are imaging magnification, the height of the processing nozzle 9 from the workpiece W (the distance between the processing nozzle 9 and the workpiece W), the positional relationship between the imaging position of the imaging optical system 5 and the position of the workpiece W in the Z-axis direction, the positional relationship between the optical components, the processing speed, the laser output value, the pulse frequency of the laser L, the duty cycle of the pulse of the laser L, the processing nozzle diameter, the type of laser beam mode, the positional relationship between the center of the processing nozzle hole and the laser beam, etc.

[0048] In addition, among the processing parameters, there are parameters with a certain processing margin, such as cutting speed, imaging position, laser output, etc. Here, the processing margin refers to the range (the range of change of processing parameters) within which the same processing quality can be achieved even if the processing parameters are changed.

[0049] The laser processing device 100 of embodiment 1 corrects the processing parameters in consideration of the change in the imaging performance of the imaging optical system 5, and thus can fully suppress the degradation of the laser processing quality. In addition, in the laser processing device 100, the temperature sensor 7 is installed in the gripping portion (optical component holder 6) that grips the optical component. Thus, the laser processing device 100 can estimate the influence of the purge gas contained in the processing head 3 and the cooling effect of the optical component holder 6 on the heat conduction given to the optical component. Therefore, the laser processing device 100 can estimate the state change such as the temperature change of the processing head 3, and can estimate the imaging performance change amount in detail and in real time.

[0050] Next, the functional structure of the laser processing apparatus 100 will be described. Figure 41 is a block diagram showing the functional structure of the laser processing device according to Embodiment 1. The laser processing device 100 includes a laser processing unit 101 and a processing control unit 102 as a control device. The laser processing unit 101 and the processing control unit 102 may be connected via a network or the like.

[0051] The laser processing unit 101 includes a laser oscillator 1, an optical fiber 2 (in Figure 4 The processing head 3 includes a temperature sensor 7, an optical component 30, and a drive unit 10X. The optical component 30 includes a collimating lens 4, an imaging optical system 5, etc. The drive unit 10X includes drive units 10B, 10C, etc. Figure 4 In the figure, the optical component holder 6, the protective glass 8, the processing nozzle 9 and the driving unit 10A are omitted.

[0052] The process control section 102 includes a process parameter input section 13 , a beam characteristic calculation section 14 , an optical component temperature estimation section 15 , a thermal lens estimation section 16 , an imaging performance change estimation section 17 , a correction amount calculation section 22 , and a control section 11 .

[0053] The processing parameter input unit 13 receives the processing parameter P1 input from outside the laser processing apparatus 100 and outputs it to the beam characteristic calculation unit 14. The processing parameter P1 received by the processing parameter input unit 13 and the processing parameter P1 corrected by the control unit 11 may be different processing parameters.

[0054] The beam characteristic calculation unit 14 receives the processing parameter P1 sent from the processing parameter input unit 13. The beam characteristic calculation unit 14 also receives laser output information P4 sent from an output monitor mounted on the laser oscillator 1. The laser output information P4 is information indicating an output value of the laser light L.

[0055] The beam characteristic calculation unit 14 may extract the laser output information P4 from the processing parameter P1 outputted from the processing parameter input unit 13. The beam characteristic calculation unit 14 may also calculate the laser output information P4 based on the laser output command P7 actually outputted from the control unit 11 to the laser oscillator 1.

[0056] The beam characteristic calculation unit 14 extracts the optical component position information P3 indicating the position of the optical component 30 from the processing parameter P1 received via the processing parameter input unit 13. The beam characteristic calculation unit 14 performs ray tracing using the laser output information P4 and the optical component position information P3, thereby calculating one or more beam characteristics of the beam diameter, the incident angle, the emission angle from the optical component 30, and the beam intensity of the laser light L irradiated to each optical component 30. The beam characteristic calculation unit 14 outputs the calculated beam characteristics to the optical component temperature estimation unit 15. In addition, the beam characteristic calculation unit 14 outputs the optical component position information P3 (lens position, etc.) and the calculated beam diameter to the thermal lens estimation unit 16.

[0057] Furthermore, the beam characteristic calculation unit 14 may calculate the optical component position information P3 based on the position command actually outputted by the driving unit 10X to the optical component 30 or the optical component holder 6 .

[0058] In addition, the beam characteristic calculation unit 14 may also calculate the optical component position information P3 based on the drive command (command for moving the optical component 30) actually outputted from the control unit 11 to the drive unit 10X. In addition, the beam characteristic calculation unit 14 may also calculate the optical component position information P3 based on the imaging magnification, the height of the processing nozzle 9 from the workpiece W, the positional relationship between the imaging position and the workpiece W, etc. included in the processing parameters P1.

[0059] The optical component temperature estimating unit 15 receives the beam characteristics of each optical component 30 from the beam characteristics calculating unit 14, and receives the temperature information P5 from the temperature sensor 7 disposed in the processing head 3. The temperature information P5 is information on the temperature of the optical component 30. The optical component temperature estimating unit 15 estimates the temperature distribution (estimated temperature) of the optical component 30 based on the received temperature information P5 and the beam characteristics. Specifically, the optical component temperature estimating unit 15 estimates the temperature distribution of the optical component 30 by considering the heating effect of the optical component 30 absorbing the laser light L, the cooling effect obtained by the water channel 12 of the optical component holder 6, and the cooling effect of the atmosphere in the processing head 3. In addition, the optical component temperature estimating unit 15 only needs to estimate the temperature of at least one point on the surface or inside of the optical component 30. The optical component temperature estimating unit 15 outputs the calculated temperature distribution of the optical component 30 to the thermal lens estimating unit 16. The calculation method of the temperature distribution will be described later.

[0060] The thermal lens estimating unit 16 estimates the thermal lens amount of each optical component 30 based on the information received from the optical component temperature estimating unit 15 and the information received from the beam characteristic calculating unit 14. Specifically, the thermal lens estimating unit 16 estimates the thermal lens amount of each optical component 30 based on the temperature distribution of the optical component 30, the optical component position information P3, and the beam diameter. The thermal lens estimating unit 16 calculates the thermal lens amount as a virtual lens having a focal length. The thermal lens estimating unit 16 outputs the calculated thermal lens amount to the imaging performance change estimating unit 17.

[0061] The imaging performance change estimation unit 17 receives the thermal lens amount of each optical component 30 from the thermal lens estimation unit 16. The imaging performance change estimation unit 17 estimates the imaging performance change amount (estimated imaging performance change amount) in the workpiece W based on the thermal lens amount of each optical component 30. Specifically, the imaging performance change estimation unit 17 estimates the imaging performance change amount in view of the processing optical system of the processing head 3, thereby estimating the imaging performance change amount in the workpiece W. The imaging performance change amount is the change amount of the imaging performance before and after the processing starts.

[0062] That is, the imaging performance change here is the imaging performance at the start of processing as a reference. The start of processing may be the start of the processing program, or it may be the timing when the laser output value in the laser output information P4 becomes 0 [W] and after a specific time, the laser output in the laser output information P4 becomes a specific value. The imaging performance change estimation unit 17 outputs the estimated imaging performance change to the correction amount calculation unit 22.

[0063] The correction amount calculation unit 22 calculates the correction amount for restoring the imaging performance to the state before the start of processing based on the received imaging performance change amount. The correction amount is, for example, a position correction amount for correcting the position of the optical component 30. In other words, the correction amount is a correction amount for correcting the imaging performance.

[0064] The correction amount calculation unit 22 outputs the calculated correction amount to the control unit 11. The control unit 11 controls at least one of the laser oscillator 1 and the processing head 3 based on the correction amount so that the evaluation value of the imaging performance becomes constant. When the control unit 11 controls the laser oscillator 1, it outputs the laser output instruction P7 to the laser oscillator 1. When the control unit 11 controls the optical component 30 in the processing head 3, it outputs the optical component displacement amount P6 to the driving unit 10X. In addition, the control unit 11 can also adjust the position of the processing head 3 based on the correction amount so that the evaluation value of the imaging performance becomes constant.

[0065] The control unit 11 outputs an optical component displacement amount P6 for controlling the position of the optical component 30, for example, using a position instruction to the optical component 30 specified by a machining program and a correction amount of the position instruction of the optical component 30. The optical component displacement amount P6 includes an instruction for controlling the position of the collimating lens 4, an instruction for controlling the position of the imaging optical system 5, and the like.

[0066] In addition, the control unit 11 outputs a laser output instruction P7 for controlling the laser output of the laser oscillator 1, for example, using the output instruction of the laser L to the laser oscillator 1 and the correction amount of the output instruction of the laser L specified by the processing program. The laser output instruction P7 includes the laser output value, the pulse frequency of the laser L, the duty cycle of the pulse of the laser L, the type of laser beam mode, etc.

[0067] The smaller the change in the position of the imaging point from the start of processing, the higher the evaluation value of the imaging performance becomes. That is, the evaluation value of the imaging performance is the change in the position of the imaging point based on the start of processing. Therefore, the control unit 11 adjusts the position of the optical component 30 so that the evaluation value of the imaging performance becomes constant, thereby maintaining the imaging performance at the start of processing.

[0068] In addition, the control unit 11 can also maintain good processing by adjusting processing parameters other than the processing parameter P1 adjusted to correct the imaging performance. In addition, the control unit 11 is not limited to adjusting the processing parameter P1 so that the evaluation value of the imaging performance becomes constant, and the processing parameter P1 can also be adjusted so that the evaluation value falls within a specific range. For example, if it is an imaging position, the specific range is the margin of the change amount of the imaging position.

[0069] Figure 5 1 is a flowchart showing the processing sequence of the processing control performed by the processing control unit of the laser processing device involved in Embodiment 1. The beam characteristic calculation unit 14 obtains the processing parameter P1 and the laser output information P4 (step S10). Specifically, the beam characteristic calculation unit 14 obtains the processing parameter P1 from the processing parameter input unit 13 and obtains the laser output information P4 from the output monitor mounted on the laser oscillator 1.

[0070] The beam characteristic calculation unit 14 extracts the optical component position information P3 indicating the position of the optical component 30 from the processing parameter P1 obtained via the processing parameter input unit 13. The beam characteristic calculation unit 14 performs ray tracing using the laser output information P4 and the optical component position information P3, thereby calculating the beam characteristic of the laser light L irradiated to each optical component 30 (step S20). The beam characteristic calculation unit 14 sends the calculated beam characteristic to the optical component temperature estimation unit 15.

[0071] The optical component temperature estimation unit 15 obtains the beam characteristics of each optical component 30 from the beam characteristics calculation unit 14, and obtains the temperature information P5 from the temperature sensor 7 disposed in the processing head 3 (step S30). In addition, the process of obtaining the temperature information P5 by the optical component temperature estimation unit 15 may be performed before the process of step S20, or may be performed before the process of step S10.

[0072] The optical component temperature estimating unit 15 estimates the temperature distribution of the optical component 30 based on the acquired temperature information P5 and the beam characteristics (step S40 ). The optical component temperature estimating unit 15 sends the calculated temperature distribution to the thermal lens estimating unit 16 .

[0073] The thermal lens estimator 16 estimates the thermal lens amount of each optical component 30 based on the temperature distribution received from the optical component temperature estimator 15 (step S50 ). The thermal lens estimator 16 sends the estimated thermal lens amount of each optical component 30 to the imaging performance change estimator 17 .

[0074] The imaging performance change estimating unit 17 estimates the imaging performance change amount in the workpiece W based on the thermal lens amount of each optical component 30 received from the thermal lens estimating unit 16 (step S60 ). The imaging performance change estimating unit 17 sends the estimated imaging performance change amount to the correction amount calculating unit 22 .

[0075] The correction amount calculation unit 22 calculates the correction amount for correcting the imaging performance based on the imaging performance change amount received from the imaging performance change estimation unit 17 (step S70). The correction amount calculation unit 22 outputs the correction amount to the control unit 11. The control unit 11 corrects the imaging performance by outputting a position instruction corresponding to the correction amount to the laser processing unit 101 (step S80). In addition, the control unit 11 may also output the position instruction corresponding to the correction amount to the drive unit 10X or to the drive unit 10A.

[0076] Here, a comparative example laser processing device is described. The comparative example laser processing device detects the lens temperature by, for example, a temperature sensor provided on the lens in the processing head, and adjusts the focal position based on the lens temperature. In the case of the comparative example laser processing device, it is impossible to estimate the influence of the atmosphere in the processing head, and therefore it is difficult to accurately adjust the focal position. In addition, in the case of the comparative example laser processing device, it is impossible to consider the influence of the laser output, and therefore it is impossible to reflect the change in the imaging position during laser processing in the control of focusing. Therefore, it is impossible to suppress the deterioration of the processing quality of the laser processing caused by the change in the imaging performance of the imaging optical system, and it is impossible to maintain the processing quality.

[0077] On the other hand, in Embodiment 1, the processing control unit 102 estimates changes in the imaging performance of the imaging optical system 5 based on the laser output information P4, the optical component position information P3, and the temperature information P5, and corrects the imaging position, thereby being able to accurately adjust the imaging position.

[0078] Here, a method of estimating the temperature of the optical component 30 by the optical component temperature estimating unit 15 will be described. Here, as an example for obtaining the temperature distribution of the optical component 30, a method of obtaining the temperatures of two points in the optical component 30 will be described.

[0079] If the absorption rate of the laser L in one optical component 30 is set to α, the mass of the optical component 30 is set to m [kg], the specific heat is set to c [J / kg·K], the laser output irradiated to the optical component 30 is set to P, τ is set to the time constant, and (i) is set to the calculation step of the step time, then the temperature rise dT(i) of the optical component 30 irradiated by the laser L with a step time dt can be approximated by the following formula (1).

[0080] [Formula 1]

[0081] dT(i)=αP(i)*(1 / mc)dt / τ…(1)

[0082] In addition, since the absorption coefficient α, mass m, and specific heat c are constants, α, m, and c can be expressed as one constant from the perspective of simplifying the management of the calculated parameters. In addition, since the time constant τ changes according to the beam diameter of the irradiated laser L, the optical component temperature estimation unit 15 changes the time constant τ according to the beam diameter calculated by the beam characteristic calculation unit 14. In addition, the optical component temperature estimation unit 15 can also change the time constant τ according to the processing parameter P1 such as the imaging magnification.

[0083] In addition, the temperature rise dT(i) of the optical component 30 is different depending on the position of the optical component 30, so the optical component temperature estimating unit 15 can estimate the temperature rise dT(i) of the optical component 30 using a polynomial at the position of the optical component 30, or can estimate it using a value that approximates the beam intensity distribution of the laser L. In addition, when it is difficult to approximate the beam intensity distribution, the beam intensity distribution can be manually set as a fixed value. Here, the temperature rise component caused by the beam absorption at the center of the beam of the i-step time step is set to dTpcenter(i), and the temperature rise component at the beam end is set to dTpedge(i).

[0084] Next, the cooling effect of the optical component 30 by water cooling of the water channel 12 provided in the optical component holder 6 will be described. The temperature of the optical component holder 6 outputted by the temperature sensor 7 is referred to as temperature T H In the processing head 3, heat transfer occurs between the optical component holder 6 and the position of the beam end of the laser light L of the optical component 30. Therefore, if the temperature of the beam end is T edge , and the temperature-related parameters such as thermal resistance are set to k w , and set the time constant to τ W , then the temperature at the end of the beam is T edge and the temperature change component dT from the cooling of the optical component holder 6 c The relationship between (i) can be approximated as shown in the following formula (2).

[0085] [Formula 2]

[0086] dT c (i) = k w (T edge (i-1)-T H (i-1))dt / τ w …(2)

[0087] In addition, when the optical component holder 6 does not have the water channel 12 of the cooling structure, the parameter k can also be set to w =0, no cooling effect of water cooling.

[0088] If the temperature of the purge gas is set to T g , set the temperature at the center of the beam to T center , the temperature change component of the purge gas corresponding to the cooling effect of the purge gas in the processing head 3 (the effect of cooling the gas purged in the processing head 3) can be calculated using the parameter kg related to the temperature of the beam center and the parameter kg related to the temperature of the beam end. edge The approximation is performed as shown in the following equations (3) and (4).

[0089] [Formula 3]

[0090] dT cgcenter (i) = kg(T g -T center (i-1))dt…(3)

[0091] [Formula 4]

[0092] dT cgedge (i) = kg edge (T g -T edge (i-1))dt…(4)

[0093] dT in formula (3) cgcenter (i) is the temperature change component at the center of the beam, and dT in equation (4) cgedge (i) is the temperature change component at the beam end. T g It may be a value measured by the temperature sensor 7 of the optical component holder 6 before processing, or a value directly measured by a temperature sensor (not shown) arranged near the optical path in the processing head 3. T g may be a value calculated based on the value measured by the temperature sensor 7 during laser processing and the structure in the processing head 3. The purge gas directly cools the optical component 30, so the optical component temperature estimation unit 15 may approximate the temperature change component of the purge gas without the time constant τ. Here, the temperature T of the beam center is center (i) can be expressed as the following equation (5). In addition, the temperature T at the beam end edge (i) can be expressed as the following formula (6).

[0094] [Formula 5]

[0095] T center (i) = T center (i-1)+dTp center (i-1)+dT cgcenter (i-1)…(5)

[0096] [Formula 6]

[0097] T edge (i) = T edge (i-1)+dT edge (i-1)+dT cw (i-1)+dT cgedge (i1)…(6)

[0099] Here is the T center (i) and T edge The difference of (i), ΔT(i), can be expressed by the following equation (7).

[0100] [Formula 7]

[0101] ΔT(i)=T center (i)-T edge (i)…(7)

[0102] The optical component temperature estimation unit 15 can set ΔT(i) represented by the formula (7) as the temperature distribution. In addition, the temperature distribution of the optical component 30 is not limited to the beam center and the beam end, and a temperature estimation point between the beam center and the beam end can be added. The more the optical component temperature estimation unit 15 increases the temperature estimation points, the more detailed the temperature distribution can be estimated.

[0103] The optical component temperature estimator 15 may also estimate the temperature distribution by additionally considering other cooling components, etc. The optical component temperature estimator 15 may estimate the temperature distribution by considering, for example, heat exchange between the beam center and the beam end, that is, the influence of thermal radiation of the processing head 3, etc.

[0104] If there is no problem with the change in temperature information at one point of the optical component 30 in the temperature distribution, the optical component temperature estimating unit 15 may estimate the temperature difference at only the one point as the temperature distribution (change in temperature information P5 ).

[0105] When the laser oscillator 1 oscillates pulses faster than the processing speed of the optical component temperature estimating unit 15 , the beam characteristic calculating unit 14 calculates the laser output [W] as the laser output information P4 as the average output between the processings of the optical component temperature estimating unit 15 .

[0106] In the above description, the optical component temperature estimation unit 15 refers to only the value of one step before the step time, but the optical component temperature estimation unit 15 may refer to the value of multiple steps before. In addition, when the SN (Signal to Noise) ratio of the temperature sensor 7 is poor, the optical component temperature estimation unit 15 may use the value obtained by taking the time average of the temperatures (temperatures at multiple points) measured by the temperature sensor 7 multiple times during a specific time as the temperature measured by the temperature sensor 7.

[0107] In the formulas (1) to (4) of the first embodiment, the case where the heat conduction equation is approximated once in time is described. However, when it is necessary to approximate the thermal conductivity characteristics of temperature more accurately, parameters related to temperature can be set after approximating with a higher degree.

[0108] When the temperature is calculated based on equations (1) to (4), the temperature is calculated by integrating equations (1) to (4) over time. The integration method is not limited to the method of integrating equations (1) to (4) over time, and the Runge-Kutta method or the like may also be used.

[0109] The parameters and the time constant τ in the optical component temperature estimation unit 15 can be obtained in advance and set in the optical component temperature estimation unit 15. The parameters and the time constant τ in the optical component temperature estimation unit 15 can be obtained in advance for each position of each optical component 30, or can be obtained in advance for each processing parameter P1. In addition, the parameters and the time constant τ in the optical component temperature estimation unit 15 can be determined by the operator when the user such as the operator starts the processing control unit 102, or can be determined by the manufacturer of the processing control unit 102 at the time of shipment.

[0110] In addition, the parameters of the optical component temperature estimation unit 15 may be determined by the operator, or by machine learning such as Bayesian heuristics, or by grid search or random heuristics, etc. The imaging performance is measured experimentally, and the parameters are determined so that the value estimated by the imaging performance change estimation unit 17 matches the measured value.

[0111] In addition, when the optical component 30 deteriorates over time, the absorption rate α of the optical component 30 to the laser light L may increase. Therefore, the parameter of the absorption rate α can be changed according to the use period of the optical component 30. In this way, the processing parameter P1 can be adjusted according to the degree of degradation of the processing head 3.

[0112] Next, a description will be given of a method for calculating the thermal lens amount by the thermal lens estimating unit 16. The focal length f of the thermal lens of the optical component 30 can be expressed by the following equation (8).

[0113] [Formula 8]

[0114]

[0115] In formula (8), r is the beam radius, and OPD (Optical Path Difference) is the optical path difference between the light passing through the end of the beam and the light passing through the center of the beam. OPD is caused by the temperature dependence of the refractive index dn / dT and the linear expansion coefficient dl / dT of the optical component 30.

[0116] Alternatively, the thermal lens estimator 16 may calculate the optical path difference using ΔT obtained by the optical component temperature estimator 15. In this case, the thermal lens estimator 16 assumes that the refractive index of the optical component 30 is n and the thickness of the optical component 30 is l, and can calculate OPD as the optical path difference by the following equation (9).

[0117] [Formula 9]

[0118]

[0119] The thermal lens estimator 16 calculates the OPD to calculate the focal length f of the thermal lens of each optical component 30. If the thermal lens estimator 16 compares the temperature dependency dn / dT and the linear expansion coefficient dl / dT and one of them is extremely small (if the difference or ratio is less than or equal to a specific value), the smaller term is deleted to perform approximation.

[0120] In addition, the thermal lens estimating unit 16 can obtain the focal length f of the thermal lens after obtaining the plurality of focal lengths f when the optical component temperature estimating unit 15 obtains the temperatures of the plurality of optical components 30 at a plurality of points. The thermal lens estimating unit 16 outputs the calculated focal length f of the thermal lens as the thermal lens information of the optical component 30 to the imaging performance change estimating unit 17.

[0121] The imaging performance change estimation unit 17 estimates the evaluation value of the imaging performance in consideration of the overall optical system of the processing head 3, thereby estimating the imaging performance change amount in the workpiece W. The imaging performance change estimation unit 17 can estimate the imaging performance change amount by ray tracing, or by paraxial ray tracing using a ray matrix, etc. Thus, the imaging performance change estimation unit 17 can estimate the imaging performance change amount during laser processing, and can output the imaging performance change amount to the control unit 11 during laser processing.

[0122] The laser processing device 100 compares the position of the imaging point before processing with the position of the imaging point after processing, thereby calculating the imaging performance change amount generated during laser processing, and correcting the processing parameter P1 with the imaging performance change amount. As a result, the laser processing device 100 can accurately estimate the position deviation amount of the imaging point and accurately correct the position deviation amount of the imaging point. Therefore, the laser processing device 100 can perform processing with a stable processing parameter P1, thereby suppressing processing defects. That is, the laser processing device 100 can suppress the deterioration of laser processing quality.

[0123] When the workpiece W is metal or the like to be processed using the high-power laser light L, the laser processing apparatus 100 can further suppress the degradation of the laser processing quality by correcting the processing parameter P1 according to the change in imaging performance.

[0124] In addition, the laser processing device 100 estimates the imaging performance only from the information (processing parameter P1) input to the processing parameter input unit 13, the information (temperature information P5) obtained from the temperature sensor 7 in the processing head 3, and the information (laser output information P4) obtained from the laser oscillator 1. Therefore, the laser processing device 100 can estimate the imaging performance robustly with respect to external factors generated during laser processing, such as changes in the material of the workpiece W and the temperature of the workpiece W.

[0125] In addition, when estimating the temperature of the optical component 30, the laser processing apparatus 100 estimates the temperature of the optical component 30 in a time series by taking into account the value of the step time one step before. That is, the optical component temperature estimating unit 15 estimates the temperature of the optical component 30 for a plurality of times in a time series, and when estimating, estimates the temperature of the optical component 30 based on the temperature of the time at least one step before the estimated time. Thus, the laser processing apparatus 100 can reduce the calculation process because it can take into account the value of the temperature at the time of the calculation step before the estimated time of the temperature of the optical component 30, and can accurately estimate the temperature even if there is a change in the output of the laser L. That is, the laser processing apparatus 100 can accurately estimate the temperature of the optical component 30 according to the change in the output of the laser L, and the calculation process becomes easy. In addition, the laser processing apparatus 100 can estimate the temperature of the optical component 30 by taking into account the values ​​of the plurality of steps before, if it does not affect the calculation load.

[0126] The control unit 11 can move the position of the optical component 30 so that if the degradation of the imaging performance affects the processing, the cause of the degradation is corrected. The priority of correction when the imaging performance changes due to the thermal lens effect can be determined by the operator. In addition, the control unit 11 can change the processing parameter P1 such as the position relationship of the optical component 30 according to the priority of the correction. For example, when the control unit 11 is set to correct the change in the imaging position with priority, the imaging position can be corrected by moving the position of the imaging optical system 5. In addition, when the control unit 11 is set to correct the aberration with priority, the collimating lens 4 and at least one of the imaging optical system 5 can be moved to correct the aberration. In addition, the control unit 11 can assign weights to the change in the imaging position, the aberration amount, etc., and use the imaging performance as one evaluation value, and adjust the processing parameter P1 so that the evaluation value of the imaging performance becomes constant.

[0127] In addition, the laser processing device 100 can estimate the influence of the purge gas contained in the processing head 3 and the influence of the heat transfer to the optical component 30 caused by the optical component holder 6. In this case, the optical component temperature estimating unit 15 estimates the temperature of at least one point on the surface or inside of the optical component 30, thereby estimating the state change such as the temperature change of the processing head 3. Therefore, the optical component temperature estimating unit 15 can estimate the imaging performance change amount in detail and in real time.

[0128] In addition, the positional relationship between the temperature sensor 7 of the optical component holder 6 and the water channel 12 is arbitrary. The temperature sensor 7 only needs to be able to measure the influence of the temperature generated by the water channel 12. In addition, the temperature sensor 7 can be arranged in the atmosphere of the processing head 3. In this case, the optical component temperature estimating unit 15 can directly estimate the temperature of the purge gas.

[0129] Furthermore, when no temperature sensor 7 is mounted on any of the optical component holders 6 , the laser processing apparatus 100 can estimate the temperature of the optical component 30 without the temperature sensor 7 using information from the temperature sensor 7 disposed near the optical component 30 .

[0130] Furthermore, the laser processing apparatus 100 can estimate the temperature of the optical component 30 without the temperature sensor 7 based on at least one of the information on the structure of the optical component holder 6 and the temperature information P5 obtained from the optical component 30 having a small irradiation beam diameter.

[0131] In addition, when the laser processing device 100 is not equipped with a temperature sensor 7 for an optical component 30 with little light change such as a protective glass 8, the absorption rate α of the laser L of the optical component 30 arranged in the front section or the optical component 30 arranged in the rear section can be set to 2 times, thereby saving processing such as calculation of the component not equipped with the temperature sensor 7.

[0132] Furthermore, when a plurality of optical components 30 are placed in one optical component holder 6 such as a lens assembly, the laser processing device 100 can perform processing such as multiplying the absorption rate α of the laser light L by the number of lens assembly sheets.

[0133] In order to correct the change in imaging performance during laser processing, the control unit 11 specifies the change of processing parameters P1 such as the positional relationship of the optical component 30 and the displacement of the optical component 30 (curvature of the reflector, etc.) to the drive unit 10X. Here, the so-called laser processing can be a period during which the laser L oscillates to process a component, or a period during which the oscillation of the laser L stops during the processing of a component. The period during which the oscillation of the laser L stops during the processing of a component is, for example, a period during which a processing switch is performed from a hole-opening process such as a punching process to a cutting process such as a cutting process. The control unit 11 adjusts the imaging performance by specifying the change of the processing parameters P1 to the drive unit 10X during laser processing.

[0134] In addition, the control unit 11 may move the optical component 30 while the machining head 3 moves to machine the next component during the execution of a program for cutting a plurality of components from one workpiece W. In addition, the control unit 11 may move the optical component 30 from the time when the output of the laser light L becomes 0 until a specific time has passed.

[0135] In addition, the control unit 11 can change the timing of changing the processing parameter P1 for each control cycle of the control unit 11, and can also change it when the processing head 3 reaches a specific movement amount. The value of the specific movement amount here can be changed according to the processing parameter P1 and the material to be processed. As described above, the laser processing device 100 can perform processing without changing the processing quality even for a large workpiece W or other parts that take a long time to process by correcting the imaging performance during laser processing.

[0136] In addition, when the value of the temperature information P5 from the temperature sensor 7 is higher than a specific value and there is a high possibility that processing failure will occur even if the imaging performance is corrected, the control unit 11 may output a command such as stopping the processing to the laser processing unit 101 because there is a possibility of damage to the optical component 30. Thus, the laser processing device 100 can detect the situation in which processing failure will continue to occur during laser processing and prevent the continuation of processing failure.

[0137] The laser processing described in the first embodiment may be any processing such as cutting, welding, drilling, lamination, etc. The material of the workpiece W processed by the laser may be any material such as metal or resin.

[0138] As described above, the laser processing device 100 of the first embodiment estimates the estimated temperature (temperature distribution) of the optical component 30 based on the beam characteristics of the laser L irradiated to the optical component 30 arranged in the processing head 3 and the temperature information P5 measured by the temperature sensor 7 arranged in the processing head 3. In addition, the laser processing device 100 estimates the thermal lens amount of the optical component 30 based on the temperature distribution, and estimates the amount of change in imaging performance based on the thermal lens amount. In addition, the laser processing device 100 calculates the correction amount of the processing parameter P1 based on the estimated amount of change in imaging performance, and changes the processing parameter P1 based on the correction amount during laser processing. As a result, the laser processing device 100 can perform laser processing in consideration of the change in imaging performance of the imaging optical system 5, and thus can fully suppress the deterioration of the laser processing quality. In addition, since the laser processing device 100 estimates the amount of change in imaging performance, it can perform correction even without considering the absolute value of the processing parameter P1.

[0139] Implementation method 2.

[0140] Next, use Figure 6 Embodiment 2 will be described. In Embodiment 2, when the laser output value is 0 [W] for a period of time equal to or longer than a specific period, there is a high possibility that the temperature of the purge gas has changed, and therefore the temperature information of the purge gas is updated.

[0141] Figure 6 Detailed description of the invention Figure 2 is a block diagram showing the functional structure of the laser processing device according to the second embodiment. Figure 6 Among the structural elements of Figure 4 In the laser processing apparatus 100 of the illustrated first embodiment, components having the same functions are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0142] The laser processing device 200 includes a laser processing unit 201 and a processing control unit 202. The laser processing unit 201 has the same configuration as the laser processing unit 101. The processing control unit 202 includes a temperature information initialization time setting unit 18 in addition to the components of the processing control unit 102.

[0143] The temperature information initialization time setting unit 18 is connected to the optical component temperature estimating unit 15. The optical component temperature estimating unit 15 of the second embodiment is connected to the laser oscillator 1, and acquires the laser output information P4 from the output monitor mounted on the laser oscillator 1.

[0144] When the laser processing device 200 performs laser processing, it may process a plurality of identical or different parts from a single large workpiece W. In this case, in the laser processing device 200, the temperature of the purge gas in the processing head 3 used by the optical component temperature estimating unit 15 may not be cooled down or may be completely cooled down.

[0145] The imaging performance change amount varies depending on the temperature of the purge gas, so the laser processing device 200 of the second embodiment updates the initial temperature of the purge gas based on the output state of the laser L that affects the temperature of the purge gas. The initial temperature of the purge gas is the temperature change component dT of the beam center described above. cgcenter (i) and the temperature change component dT at the beam end cgedge The temperature used in the calculation of (i) is thus the temperature change component dT at the center of the aforementioned beam. cgcenter (i) and the temperature change component dT at the beam end cgedge (i) It becomes an appropriate value corresponding to the temperature of the purge gas.

[0146] The temperature information initialization time setting unit 18 updates at least one of the initial temperature of the purge gas and the initial temperature of the atmosphere temperature of the processing head 3 when there is no oscillation of the laser light L, that is, when the laser output value is 0 [W] for a period of time greater than or equal to a specific time. For example, when the laser output value is 0 [W] for a period of time greater than or equal to a specific time, the temperature information initialization time setting unit 18 outputs an instruction (initial temperature update instruction) for updating the initial temperature of the purge gas and the initial temperature of the atmosphere temperature of the processing head 3 to the optical component temperature estimating unit 15. In addition, when the state of the laser output value being near 0 [W] (less than a specific value) for a period of time greater than or equal to a specific time, the temperature information initialization time setting unit 18 may output the initial temperature update instruction to the optical component temperature estimating unit 15.

[0147] As described above, the temperature information initialization time setting unit 18 outputs an initial temperature update instruction to the optical component temperature estimation unit 15 if the laser output value is less than a specific value (for example, 0 [W]) during the set specific time period. The initial temperature update instruction causes the optical component temperature estimation unit 15 to update the temperature of the stored purge gas to the value of the latest temperature information P5 output by the temperature sensor 7 at this time (when the initial temperature update instruction is received).

[0148] When the optical component temperature estimation unit 15 receives the initial temperature update command, it updates the currently stored temperature of the purge gas to the value of the latest temperature information P5 output by the temperature sensor 7 when the initial temperature update command is received. In addition, the optical component temperature estimation unit 15 estimates the temperature distribution of the optical component 30 based on the updated temperature information P5 and the beam characteristics received from the beam characteristics calculation unit 14.

[0149] Thus, the laser processing device 200 can also cope with the temperature change of the purge gas in the processing head 3, the temperature change of the surrounding environment, etc., and can perform processing after estimating the imaging performance suitable for the environment. In addition, the time setting for initializing the temperature information to the temperature information initialization time setting unit 18 can be set by the operator, can be set in advance when the processing control unit 202 is started, and can be set when the processing control unit 202 is shipped.

[0150] In addition, the temperature information initialization time setting unit 18 may have a function of initializing the deviation of the imaging position to 0 [mm], etc., if the laser output value is 0 [W] for a specific time, so as to initialize the imaging performance change amount that changes due to the thermal lens effect. Thus, the laser processing device 200 does not displace the optical component 30 when it does not actually contribute to the processing, so that the life of the driving unit 10X can be extended.

[0151] As described above, in Embodiment 2, when the laser output value is 0 [W] for a period of time greater than or equal to a specific time, the laser processing device 200 has a high probability of a change in the temperature of the purge gas, and therefore updates the temperature information of the purge gas. As a result, the laser processing device 200 can accurately estimate the state of the atmosphere before the start of processing in the processing head 3. Therefore, the laser processing device 200 can perform processing after estimating the imaging performance corresponding to the temperature change of the purge gas in the processing head 3, the temperature change of the surrounding environment, etc. Therefore, the laser processing device 200 can fully suppress the deterioration of the laser processing quality.

[0152] Implementation method 3.

[0153] Next, use Figure 7 Embodiment 3 will be described. The laser processing apparatus of Embodiment 3 corrects the imaging performance change amount estimated by the imaging performance change estimating unit 17 based on processing type information indicating the type of laser processing, such as the material and thickness of the workpiece W and the type of processing gas.

[0154] Figure 7 Detailed description of the invention Figure 2 is a block diagram showing the functional structure of the laser processing device according to the third embodiment. Figure 7 Among the structural elements of Figure 4 In the laser processing apparatus 100 of the illustrated first embodiment, components having the same functions are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0155] The laser processing device 300 includes a laser processing unit 301 and a processing control unit 302. The laser processing unit 301 has the same structure as the laser processing unit 101. The processing control unit 302 further includes a correction coefficient determination unit 19 in addition to the structural elements included in the processing control unit 102 or the structural elements included in the processing control unit 202. Next, a case where the processing control unit 302 further includes a correction coefficient determination unit 19 in addition to the structural elements included in the processing control unit 102 will be described.

[0156] The processing parameter input unit 13 of the processing control unit 302 extracts information indicating the material of the workpiece W (material P21), information indicating the plate thickness of the workpiece W (plate thickness P22), and information on the type of processing gas used in laser processing (gas type P23) from the processing parameter P1, and outputs them to the correction coefficient determination unit 19. The processing gas used in the laser processing is a gas (assist gas) ejected to the workpiece W when the laser L is irradiated to the workpiece W.

[0157] The correction coefficient determination unit 19 is connected to the processing parameter input unit 13 and the correction amount calculation unit 22. The correction coefficient determination unit 19 receives the material P21, the plate thickness P22, and the gas type P23 from the processing parameter input unit 13 as processing type information. The correction coefficient determination unit 19 determines a correction coefficient k corresponding to at least one of the material P21, the plate thickness P22, and the gas type P23. The correction coefficient k is a coefficient for correcting the imaging performance change amount. The correction coefficient determination unit 19 outputs the determined correction coefficient k to the correction amount calculation unit 22.

[0158] The correction amount calculation unit 22 receives the correction coefficient k from the correction coefficient determination unit 19 and receives the imaging performance change amount from the imaging performance change estimation unit 17. The correction amount calculation unit 22 calculates the corrected deviation amount Δf by multiplying the correction coefficient k for correcting Δf by Δf, while setting the imaging performance change amount estimated by the imaging performance change estimation unit 17 as the deviation amount Δf of the imaging position. corr Specifically, the correction amount calculation unit 22 calculates the corrected deviation amount Δf using the following equation (10): corr Perform calculations.

[0159] [Formula 10]

[0160] Δf corr =k△f…(10)

[0161] The correction amount calculation unit 22 calculates the amount of deviation Δf after correction based on the amount of deviation Δf after correction. corr The correction amount calculation unit 22 calculates the correction amount for returning the imaging performance to the state before the start of processing. The correction amount calculation unit 22 outputs the calculated correction amount to the control unit 11.

[0162] The laser processing device 300 may know in advance whether the processing margin of the imaging position at the start of processing corresponding to the material P21, the plate thickness P22, and the gas type P23 is in the direction of the processing head 3 or in the depth direction of the workpiece W compared to the surface of the workpiece W. In this case, the laser processing device 300 can multiply the correction coefficient k corresponding to the processing margin of the imaging position by the deviation Δf.

[0163] For example, for the cutting process in which the material to be processed is mild steel SS400 and the gas type P23 is oxygen, it is allowed to set the correction coefficient k so that the imaging position of the imaging point is moved in the direction of the processing head 3. Therefore, in this case, as the correction coefficient k for avoiding the imaging position of the imaging point from being moved in the depth direction of the workpiece W, a value less than or equal to 1.0 is set, for example.

[0164] In addition, for the cut-off process when the gas type P23 is nitrogen, avoid setting the correction coefficient k that moves the imaging position of the imaging point in the direction of the processing head 3. Therefore, in this case, it is allowed to move the imaging position of the imaging point in the depth direction of the workpiece W, so as to set the correction coefficient k to a value greater than or equal to 1.0, for example.

[0165] Thus, the laser processing apparatus 300 can correct the imaging performance according to the processing type information such as the material P21, the plate thickness P22, and the gas type P23, and can perform processing corresponding to the working environment.

[0166] The correction amount calculation unit 22 calculates the correction amount based on the corrected imaging performance change amount (corrected deviation amount Δf corr ) calculates the correction amount of the processing parameter P1. The correction amount calculation unit 22 outputs the correction amount of the processing parameter P1 to the control unit 11. The control unit 11 adjusts the optical component 30 based on the correction amount so that the evaluation value of the imaging performance becomes constant. The control unit 11 inputs the instruction for adjusting the optical component 30 (the movement instruction of the optical component 30, etc.) to the driving unit 10X, thereby changing the position of the optical component 30 during the laser processing and controlling the laser processing. As described above, the control unit 11 performs control corresponding to the evaluation value of the imaging performance (imaging performance change amount) after multiplication by the correction coefficient k.

[0167] As described above, in Embodiment 3, the laser processing device 300 corrects the imaging performance variation according to the material P21, the plate thickness P22, and the gas type P23. Thus, the laser processing device 300 can correct the processing parameter P1 with the correction amount corresponding to the imaging performance variation corrected according to the material P21, the plate thickness P22, and the gas type P23, and then perform processing. Therefore, the laser processing device 300 can fully suppress the deterioration of the laser processing quality.

[0168] Implementation method 4.

[0169] Next, use Figure 8 and Fig. 9 Embodiment 4 is described. In embodiment 4, the laser processing device learns the correspondence between the processing parameter P1, the optical component position information P3, the laser output information P4 and the temperature information P5 and the imaging performance change amount to create a trained model. Furthermore, during laser processing, the laser processing device estimates the imaging performance change amount by inputting the processing parameter P1, the optical component position information P3, the laser output information P4 and the temperature information P5 into the trained model.

[0170] Figure 8Detailed description of the invention Figure 2 is a block diagram showing the functional structure of a laser processing device according to Embodiment 4. Figure 8 Among the structural elements of Figure 4 In the laser processing apparatus 100 of the illustrated first embodiment, components having the same functions are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0171] The laser processing device 400 includes a laser processing unit 401 and a processing control unit 402. The laser processing unit 401 has the same structure as the laser processing unit 101. The processing control unit 402 further includes a processing parameter analyzer 20 as a machine learning device in addition to the structural elements of the processing control unit 102, the structural elements of the processing control unit 202, or the structural elements of the processing control unit 302. Next, a case where the processing control unit 402 further includes the processing parameter analyzer 20 in addition to the structural elements of the processing control unit 102 will be described.

[0172] The processing parameter analyzer 20 includes a data acquisition unit 21, a feature extraction unit 23, a learning unit 24, and a correction amount calculation unit 22. The data acquisition unit 21 is connected to the processing parameter input unit 13, the laser oscillator 1, the temperature sensor 7, and the feature extraction unit 23. The learning unit 24 is connected to the feature extraction unit 23 and the correction amount calculation unit 22.

[0173] The data acquisition unit 21 acquires the processing parameter P1 and the optical component position information P3 from the processing parameter input unit 13. In addition, the data acquisition unit 21 acquires the temperature information P5 from the temperature sensor 7. In addition, the data acquisition unit 21 acquires the laser output information P4 from the laser oscillator 1. Here, the laser output information P4 is the first output value of the laser light L, and the temperature information P5 is the first temperature information.

[0174] In addition, the data acquisition unit 21 can extract the laser output information P4 from the processing parameter P1 outputted via the processing parameter input unit 13 as in Embodiment 1. In addition, the data acquisition unit 21 can also calculate the laser output information P4 based on the output command of the laser L actually outputted from the control unit 11 to the laser oscillator 1.

[0175] In addition, the data acquisition unit 21 acquires the laser output history which is the time series data of the laser output and the temperature history which is the time series data of the measurement result of the temperature sensor 7. Specifically, the data acquisition unit 21 generates the laser output history based on the laser output information P4. In addition, the data acquisition unit 21 generates the temperature history based on the temperature information P5.

[0176] The laser output history is the time transition of the laser output. The laser output history may be the average output of the laser L or the peak output. The laser output history may be data as long as the time transition of the output is known. The data acquisition unit 21 acquires the laser output history at a sampling period that the data acquisition unit 21 can acquire.

[0177] The data acquisition unit 21 outputs the acquired processing parameter P1, optical component position information P3, laser output history, and temperature history as state quantities to the feature quantity extraction unit 23. In addition, the data acquisition unit 21 may acquire a first state quantity including at least the laser output information P4 and the temperature information P5 and output it to the feature quantity extraction unit 23. In addition, the data acquisition unit 21 may output a state quantity including the laser output information P4 to the feature quantity extraction unit 23 instead of the laser output history. In addition, the data acquisition unit 21 may output a state quantity including the temperature information P5 to the feature quantity extraction unit 23 instead of the temperature history.

[0178] The feature quantity extraction unit 23 extracts feature quantities from the state quantity. The feature quantities here are information on the temperature of the optical component 30, information on the laser output, processing parameter P1, etc. The feature quantity extraction unit 23 outputs the extracted feature quantities to the learning unit 24. The feature quantities correspond to the beam characteristics and temperature information P5 described in Embodiments 1 to 3.

[0179] In addition, an evaluation value of the imaging performance is also input to the learning unit 24. The evaluation value of the imaging performance is a value corresponding to the measurement result related to the change amount of the imaging point, and can be a continuous value or a discrete value. The evaluation value of the imaging performance determined by the operator can be input to the learning unit 24, and the evaluation value of the imaging performance calculated by the imaging performance change estimation unit 17 of embodiments 1 to 3 can also be input. The evaluation value of the imaging performance determined by the operator can be input from an input unit not shown in the figure, for example, or can be received from other devices. In addition, the evaluation value can be the beam waist position, the beam diameter at the imaging position, the spherical aberration amount, etc. In addition, the evaluation value can also be whether the shape of the beam intensity distribution is good or not.

[0180] The learning unit 24 learns by associating the feature quantity extracted by the feature quantity extraction unit 23 with the evaluation value of the imaging performance. That is, the learning unit 24 learns the processing performed by the optical component temperature estimation unit 15, the thermal lens estimation unit 16, and the imaging performance change estimation unit 17. In addition, the learning unit 24 is realized by a processing circuit similarly to the processing parameter analyzer 20.

[0181] The learning unit 24 learns the set of input data and result data by machine learning, thereby generating a trained model. The learning unit 24 here learns the situation of estimating the correction amount of the processing parameter P1 based on the state amount to generate a trained model. As the algorithm of machine learning performed by the learning unit 24, any algorithm can be used. For example, the learning unit 24 can use an algorithm for learning with a teacher.

[0182] The learning unit 24 performs machine learning on imaging performance variation (variation in imaging position, variation in aberration, etc.) using a data set composed of feature quantities and evaluation values. The data set here is data in which feature quantities and evaluation values ​​are associated with each other.

[0183] The learning unit 24 uses the trained model obtained by machine learning to estimate the change of the processing parameter P1 such as the position of the imaging point corresponding to the feature quantity and the displacement of the positional relationship of the optical component 30 included in the processing head 3. Specifically, the learning unit 24 uses the trained model to derive the imaging performance change corresponding to the feature quantity. That is, the learning unit 24 obtains the second state quantity including at least the laser output information (second output value) P4 and the temperature information (first temperature information) P5 during laser processing, inputs the feature quantity (second state quantity) to the trained model, and thereby derives the imaging performance change corresponding to the second state quantity. The learning unit 24 outputs the derived imaging performance change to the correction amount calculation unit 22.

[0184] In addition, the processing parameter analyzer 20 may not include the feature amount extracting unit 23. In this case, the data acquiring unit 21 outputs the state amount to the learning unit 24. Then, the learning unit 24 performs learning using the state amount instead of the feature amount.

[0185] The correction amount calculation unit 22 calculates the correction amount of the process parameter P1 based on the imaging performance change amount (estimated amount) sent from the learning unit 24. Alternatively, the correction amount calculation unit 22 may obtain the process parameter P1 set in the control unit 11 and calculate the correction amount based on the imaging performance change amount sent from the learning unit 24 and the process parameter P1 currently set in the control unit 11. The correction amount calculation unit 22 outputs the calculated correction amount to the control unit 11.

[0186] The control unit 11 corrects the processing parameter P1 based on the correction amount received from the correction amount calculation unit 22, thereby controlling the processing. As described above, when there is a difference between the value of the processing parameter P1 corresponding to the estimated result (imaging performance change amount) obtained by the learning unit 24 and the current value of the processing parameter P1, the laser processing device 400 performs processing under the condition that the processing parameter P1 is corrected. The correction of the processing parameter P1 is repeated until the correction amount (correction amount corresponding to the deviation amount of the imaging performance change amount) output from the learning unit 24 is within a specific range. In the laser processing device 400, the control unit 11 can adjust the processing parameter P1 with high precision by outputting an instruction corresponding to the correction amount to the drive unit 10X. In addition, when the correction amount is a correction amount for correcting the position of the processing head 3, the control unit 11 outputs an instruction corresponding to the correction amount to the drive unit 10A.

[0187] In addition, in the fourth embodiment, the processing parameter analyzer 20 learns the relationship between the feature quantity and the deviation amount of the imaging performance change amount, but the processing parameter analyzer 20 may also learn the relationship between the feature quantity and the thermal lens amount. That is, the processing parameter analyzer 20 may learn the processing performed by the optical component temperature estimation unit 15 and the thermal lens estimation unit 16. In other words, in the laser processing apparatus 100, 200, 300, the optical component temperature estimation unit 15 and the thermal lens estimation unit 16 may be replaced, and the data acquisition unit 21, the feature quantity extraction unit 23 and the learning unit 24 may be configured as a machine learning device. In this case, the machine learning device receives the beam characteristics from the beam characteristics calculation unit 14 and receives the temperature information P5 from the temperature sensor 7. Moreover, the machine learning device generates a trained model representing the correspondence relationship between the feature quantity (beam characteristics and temperature information P5) and the thermal lens amount through learning. In this case, the thermal lens amount calculated by the operator is input to the machine learning device. The machine learning device estimates the thermal lens amount corresponding to the feature amount by inputting the feature amount into the trained model during laser processing. As described above, the machine learning device learns the relationship between the feature amount and the thermal lens amount of the optical component 30, and estimates the thermal lens amount corresponding to the feature amount instead of the optical component temperature estimating unit 15 and the thermal lens estimating unit 16 during laser processing.

[0188] In addition, the processing parameter analyzer 20 can learn the relationship between the feature quantity and the temperature distribution of the optical component 30. That is, the processing parameter analyzer 20 can learn the processing performed by the optical component temperature estimation unit 15. In other words, in the laser processing apparatus 100, 200, 300, the optical component temperature estimation unit 15 can be replaced, and a data acquisition unit (first data acquisition unit) 21, a feature quantity extraction unit 23, and a learning unit (first learning unit) 24 can be configured as a machine learning device (first machine learning device). In this case, the machine learning device receives the first beam characteristic from the beam characteristic calculation unit 14 and receives the temperature information (first temperature information) P5 from the temperature sensor 7. And, the machine learning device generates a first trained model representing the correspondence relationship between the feature quantity (the first state quantity including the beam characteristic and the temperature information P5) and the temperature distribution of the optical component 30 through learning. In this case, the temperature distribution of the optical component 30 calculated by the operator is input to the machine learning device. During laser processing, the machine learning device inputs the second state quantity including the second beam characteristic received from the beam characteristic calculation unit 14 and the temperature information (second temperature information) P5 received from the temperature sensor 7 into the first trained model, thereby estimating the temperature distribution of the optical component 30 corresponding to the second state quantity. As described above, the machine learning device learns the relationship between the characteristic quantity and the temperature distribution of the optical component 30, and in laser processing, replaces the beam characteristic calculation unit 14 to estimate the temperature distribution of the optical component 30 corresponding to the characteristic quantity.

[0189] In addition, the processing parameter analyzer 20 can learn the correspondence between the temperature distribution estimated by the optical component temperature estimation unit 15, the optical component position information P3 sent from the beam characteristic calculation unit 14, the beam diameter, and the thermal lens amount. That is, the processing parameter analyzer 20 can learn the processing performed by the thermal lens estimation unit 16. In other words, in the laser processing apparatus 100, 200, 300, a data acquisition unit (second data acquisition unit) 21, a feature quantity extraction unit 23, and a learning unit (second learning unit) 24 can be configured as a machine learning device (second machine learning device) instead of the thermal lens estimation unit 16. In this case, the machine learning device receives the temperature distribution (first estimated temperature) from the optical component temperature estimation unit 15. And, the machine learning device generates a second trained model representing the correspondence between the feature quantity (the third state quantity including the temperature distribution estimated by the optical component temperature estimation unit 15) and the thermal lens amount through learning. In this case, the thermal lens amount calculated by the operator is input to the machine learning device. During laser processing, the machine learning device estimates the thermal lens amount corresponding to the fourth state amount by inputting the fourth state amount including the temperature distribution (second estimated temperature) estimated by the optical component temperature estimation unit 15 into the second trained model. As described above, the machine learning device learns the relationship between the temperature distribution, the optical component position information P3 and the beam diameter and the thermal lens amount of the optical component 30, and estimates the thermal lens amount corresponding to the characteristic amount in place of the thermal lens estimation unit 16 during laser processing. In addition, the third state amount and the fourth state amount may include the optical component position information P3 and the beam diameter sent from the beam characteristic calculation unit 14.

[0190] In addition, the processing parameter analyzer 20 can learn the correspondence between the thermal lens amount estimated by the thermal lens estimation unit 16 and the imaging performance change amount or the evaluation value of the imaging performance. That is, the processing parameter analyzer 20 can learn the processing performed by the imaging performance change estimation unit 17. In other words, in the laser processing apparatus 100, 200, 300, a data acquisition unit (third data acquisition unit) 21, a feature amount extraction unit 23, and a learning unit (third learning unit) 24 can be configured as a machine learning device (third machine learning device) instead of the imaging performance change estimation unit 17. In this case, the machine learning device receives the thermal lens amount (first thermal lens amount) from the thermal lens estimation unit 16. And, the machine learning device generates a third trained model representing the correspondence between the feature amount (the fifth state amount including the thermal lens amount estimated by the thermal lens estimation unit 16) and the imaging performance change amount or the evaluation value of the imaging performance through learning. In this case, the imaging performance change amount or the evaluation value of the imaging performance calculated by the operator is input to the machine learning device. During laser processing, the machine learning device estimates the imaging performance change amount or the imaging performance evaluation value corresponding to the sixth state amount by inputting the sixth state amount including the thermal lens amount (second thermal lens amount) estimated by the thermal lens estimation unit 16 into the third trained model. As described above, the machine learning device learns the relationship between the thermal lens amount and the imaging performance change amount or the imaging performance evaluation value, and estimates the imaging performance change amount or the imaging performance evaluation value corresponding to the feature amount in place of the imaging performance change estimation unit 17 during laser processing.

[0191] In addition, the processing parameter analyzer 20 can learn the correspondence between the imaging performance change amount estimated by the imaging performance change estimation unit 17 and the correction amount of the processing parameter P1. That is, the processing parameter analyzer 20 can learn the processing performed by the correction amount calculation unit 22. In other words, in the laser processing apparatus 100, 200, 300, a data acquisition unit (fourth data acquisition unit) 21, a feature amount extraction unit 23, and a learning unit (fourth learning unit) 24 can be configured as a machine learning device (fourth machine learning device) instead of the correction amount calculation unit 22. In this case, the machine learning device receives the imaging performance change amount (first estimated imaging performance change amount) from the imaging performance change estimation unit 17. And, the machine learning device generates a fourth trained model representing the correspondence between the feature amount (the seventh state amount including the imaging performance change amount estimated by the imaging performance change estimation unit 17) and the correction amount of the processing parameter P1 through learning. In this case, the correction amount of the processing parameter P1 calculated by the operator is input to the machine learning device. During laser processing, the machine learning device estimates the correction amount of the processing parameter P1 corresponding to the eighth state amount by inputting the eighth state amount including the imaging performance change amount (second estimated imaging performance change amount) estimated by the imaging performance change estimation unit 17 into the fourth trained model. As described above, the machine learning device learns the relationship between the imaging performance change amount and the correction amount, and estimates the correction amount corresponding to the feature amount in place of the correction amount calculation unit 22 during laser processing.

[0192] Similarly, the machine learning device can learn the correspondence between the thermal lens amount estimated by the thermal lens estimating unit 16 and the correction amount of the process parameter P1. Similarly, the machine learning device can learn the correspondence between the temperature distribution estimated by the optical component temperature estimating unit 15 and the correction amount of the process parameter P1.

[0193] The machine learning device learns at least one of the processing performed by the optical component temperature estimating unit 15, the processing performed by the thermal lens estimating unit 16, the processing performed by the imaging performance change estimating unit 17, and the processing performed by the correction amount calculating unit 22. For example, the machine learning device may learn the correspondence between the temperature distribution estimated by the optical component temperature estimating unit 15 and the imaging performance change amount.

[0194] In addition, in Embodiment 4, the case where the learning unit 24 has both a learning function of machine learning the relationship between the feature quantity and the imaging performance change amount and an inference function of inferring the imaging performance change amount using the trained model is described, but the learning function and the inference function may be implemented by different devices. In other words, the inference unit that outputs the evaluation value using the trained model may be provided separately from the learning unit 24. That is, the processing parameter analyzer 20 may have an inference unit that calculates the imaging performance change amount using the trained model learned by the learning unit 24.

[0195] In addition, Figure 8 In the example shown, the learning unit 24 is provided in the processing parameter analyzer 20, but the learning unit 24 may be a separate device from the processing parameter analyzer 20. For example, the processing parameter analyzer 20 and the learning unit 24 may be connected via a network. In addition, the learning unit 24 may also exist on a cloud server.

[0196] The learning unit 24 uses a neural network model, for example, to learn the imaging performance change amount corresponding to the processing parameter P1 and the laser output information P4 through so-called teacher learning. Here, teacher learning is a machine learning that infers the result based on the input by giving a large number of sets of data of certain input and result (label) data, that is, data sets, to the learner to learn the features existing in these data sets.

[0197] A neural network is composed of an input layer composed of multiple neurons, an intermediate layer composed of multiple neurons, also called a hidden layer, and an output layer composed of multiple neurons. The intermediate layer can be one layer or more than or equal to two layers.

[0198] Fig. 9 is a diagram showing a structural example of a neural network model according to Embodiment 4. X1, X2, and X3 are neurons in the input layer, Y1 and Y2 are neurons in the middle layer, and Z1, Z2, and Z3 are neurons in the output layer. Fig. 9 In the three-layer neural network model shown, after the three input values ​​are input to the corresponding X1, X2, and X3, each input value is multiplied by the corresponding weights w11~w16 and input to the neurons of the middle layer, namely Y1 and Y2. Moreover, the output values ​​from Y1 and Y2 are multiplied by the corresponding weights w21~w26 and input to the neurons of the output layer, namely Z1, Z2, and Z3. The output layer adds the input value and outputs it as the output result. For example, the results output from Z1, Z2, and Z3 can be associated with the evaluation results corresponding to each poorly processed item. The output result changes according to the values ​​of weights w11~w16 and weights w21~w26.

[0199] In Embodiment 4, the weights w11 to w16 and weights w21 to w26 are adjusted using the above data set so that the output result of the above neural network is close to the evaluation result of the correct imaging performance (imaging performance change), thereby learning. Fig. 9 The neural network shown is an example. The number of layers of the neural network model and the number of neurons in each layer are not limited to Fig. 9 Example.

[0200] In addition, the learning unit 24 can also use a neural network model to learn the relationship between the laser output information P4, the information of the temperature sensor 7 and the evaluation results of the imaging performance, or the processing parameter P1 to be corrected through so-called unsupervised learning. Unsupervised learning is a method in which a large amount of input data is given to the learning unit 24 to learn what kind of distribution the input data forms, and even if the corresponding teacher output data is not given, a method of compressing, classifying, shaping, etc. for the input data is learned. For example, in unsupervised learning, the characteristics of the set of input data can be clustered with each other. In this case, by setting a certain benchmark so that the results of clustering, etc. are optimized, the evaluation results are distributed to the results of clustering, etc., so that the prediction of the evaluation results can be achieved. In addition, as a problem setting between unsupervised learning and teacher learning, there is a learning called semi-teacher learning, which is a group of data with input and output only in a part, and only input data exists outside. The learning unit 24 of the fourth embodiment can achieve machine learning through semi-teacher learning.

[0201] In addition, the learning unit 24 can obtain data sets from a plurality of processing parameter analyzers 20, and learn the evaluation results of imaging performance for a combination of the laser output history and the temperature history, which is the time series data of the measurement result (temperature information P5) of the temperature sensor 7. The plurality of processing parameter analyzers 20 may be the processing parameter analyzers 20 of the fourth embodiment.

[0202] In addition, the learning unit 24 may obtain data sets from a plurality of processing parameter analyzers 20 used in the same site, or may obtain data sets from a plurality of processing parameter analyzers 20 respectively operated in different sites. Furthermore, it is also possible to add a processing parameter analyzer 20 as a source of obtaining the data set in the middle, or to remove a processing parameter analyzer 20 as a source of obtaining the data set in the middle.

[0203] In addition, a learning unit may be separately provided from the processing parameter analyzer 20, and after the learning unit has learned using a data set obtained from a processing parameter analyzer (a first processing parameter analyzer), it may be connected to another processing parameter analyzer (a second processing parameter analyzer) and further obtain a data set from the second processing parameter analyzer for further learning.

[0204] The data acquisition unit 21 may also acquire the plate thickness P22 of the workpiece W, the material P21 of the workpiece W, etc. and include them in the state quantity. In this case, the feature quantity extraction unit 23 outputs the plate thickness P22 of the workpiece W, the material P21 of the workpiece W, etc., including them in the feature quantity to the learning unit 24 .

[0205] As the learning algorithm used by the learning unit 24, deep learning (Deep Learning) for learning to extract the feature quantity itself can also be used, and the learning unit 24 can perform machine learning according to other well-known methods, such as genetic programming, functional logic programming, support vector machine, Fisher discriminant method, partial space method, discriminant analysis using Mahalanobis space, etc. In addition, as the learning algorithm used by the learning unit 24, decision tree, random forest (RandomForest), logistic regression, k-nearest neighbor (kNN), partial space method, CLAFIC (CLAss-Featuring Information Compression method), Isolation Forest, LOF (Local OutlierFactor), boosting method, AdaBoost, LogitBoost, One-Class SVM (Support Vector Machine), Gaussian Mixture Model, etc. can be used. In addition, the learning unit 24 may not be provided with the feature extraction unit 23 when performing learning to automatically extract feature quantities, such as deep learning, convolutional neural network (CNN), recurrent neural network (RNN), etc. In addition, a processing parameter analyzer 20 may be provided for each item of imaging performance for the processing control unit 402, or one processing parameter analyzer 20 may correspond to an item of imaging performance. In addition, the learning unit 24 may use exploration algorithms such as reinforcement learning and Bayesian exploration to explore parameters. As described above, the processing control unit 402 has a processing parameter analyzer 20, which can estimate the imaging performance with high precision and can perform processing stably. The actions of embodiment 4 other than those described above are the same as those of embodiment 1.

[0206] As described above, the processing parameter analyzer 20 of the fourth embodiment learns the correspondence between the processing parameter P1, the optical component position information P3, the laser output information P4 and the temperature information P5 and the imaging performance change amount to generate a trained model. In addition, during laser processing, the processing parameter analyzer 20 inputs the processing parameter P1, the optical component position information P3, the laser output information P4 and the temperature information P5 into the trained model, thereby estimating the imaging performance change amount. As a result, the laser processing device 400 can perform laser processing in consideration of the change in the imaging performance of the imaging optical system 5, and thus can fully suppress the degradation of the laser processing quality.

[0207] Next, the hardware structure of the processing control units 102, 202, 302, and 402 is described. In addition, the processing control units 102, 202, 302, and 402 have the same hardware structure, so the hardware structure of the processing control unit 102 is described here. In the processing control unit 102, the processing parameter input unit 13, the beam characteristic calculation unit 14, the optical component temperature estimation unit 15, the thermal lens estimation unit 16, the imaging performance change estimation unit 17, the correction amount calculation unit 22, and the control unit 11 are implemented by a processing circuit. The processing circuit can be a processor and a memory that executes a program stored in a memory, or it can be dedicated hardware. The processing circuit is also called a control circuit.

[0208] Fig.10 This is a diagram showing a configuration example of a processing circuit when the processing circuit included in the process control unit according to the first to fourth embodiments is realized by a processor and a memory. Fig.10 The processing circuit 90 shown is a control circuit, which has a processor 91 and a memory 92. When the processing circuit 90 is composed of the processor 91 and the memory 92, each function of the processing circuit 90 is implemented by software, firmware, or a combination of software and firmware. The software or firmware is described as a program and stored in the memory 92. In the processing circuit 90, the processor 91 reads out and executes the program stored in the memory 92, thereby realizing each function. That is, the processing circuit 90 has a memory 92, and the memory 92 is used to store the processing control program in which the processing of the processing control unit 102 is finally executed. The processing control program can be said to be a program for causing the processing control unit 102 to execute each function realized by the processing circuit 90. The processing control program can be provided through a storage medium storing the program, or can be provided through other units such as a communication medium.

[0209] Here, the processor 91 is, for example, a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor), etc. In addition, the memory 92 is, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (registered trademark) (Electrically EPROM), or other non-volatile or volatile semiconductor memory, a magnetic disk, a floppy disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc), etc.

[0210] Fig.11 This is a diagram showing an example of a processing circuit in the case where the processing circuit included in the process control section according to the first to fourth embodiments is configured by dedicated hardware. Fig.11 The processing circuit 93 shown is, for example, a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

[0211] The processing circuits 90 and 93 may be partially implemented by dedicated hardware and partially implemented by software or firmware. As described above, the processing circuits 90 and 93 may implement the above functions by dedicated hardware, software, firmware or a combination thereof.

[0212] In addition, the processing parameter input unit 13, the beam characteristic calculation unit 14, the optical component temperature estimation unit 15, the thermal lens estimation unit 16, the imaging performance change estimation unit 17, the correction amount calculation unit 22 and a part of the control unit 11 can also be implemented by different processing circuits.

[0213] The configuration described in the above embodiment is merely an example, and may be combined with other known technologies, the embodiments may be combined with each other, and part of the configuration may be omitted or changed without departing from the gist.

[0214] Description of the label

[0215] 1 laser oscillator, 2 optical fiber, 3 processing head, 4 collimating lens, 5 imaging optical system, 6 optical component holder, 7 temperature sensor, 8 protective glass, 9 processing nozzle, 10A to 10C, 10X driving unit, 11 control unit, 12 water channel, 13 processing parameter input unit, 14 beam characteristic calculation unit, 15 optical component temperature estimation unit, 16 thermal lens estimation unit, 17 imaging performance change estimation unit, 18 temperature information initialization time setting unit, 19 correction coefficient determination unit, 20 processing parameter analyzer, 21 data acquisition unit, 22 correction amount calculation unit, 23 feature amount extraction unit Taking unit, 24 learning unit, 30 optical component, 90, 93 processing circuit, 91 processor, 92 memory, 100, 200, 300, 400 laser processing device, 101, 201, 301, 401 laser processing unit, 102, 202, 302, 402 processing control unit, D1, D2 imaging point position, L laser, P1 processing parameter, P21 material, P22 plate thickness, P23 gas type, P3 optical component position information, P4 laser output information, P5 temperature information, P6 optical component displacement, P7 laser output instruction, W workpiece.

Claims

1. A laser processing device, characterized in that: have: a beam characteristic calculation unit that calculates the beam characteristic of the laser beam irradiated to the optical component disposed in the processing head; a temperature estimating unit that estimates an estimated temperature of the optical component based on temperature information, which is information on a temperature measured by a temperature sensor disposed in the processing head, and the beam characteristics; a thermal lens estimating unit that estimates a thermal lens amount of the optical component based on the estimated temperature; an imaging performance change estimating unit that estimates an estimated imaging performance change amount, which is an amount of change in imaging performance of the imaging optical system of the machining head from before machining starts, based on the thermal lens amount; a correction amount calculation unit that calculates a correction amount of a processing parameter based on the estimated imaging performance change amount; and A control unit controls laser processing using the laser light and changes the processing parameter based on the correction amount during the laser processing.

2. The laser processing device according to claim 1, characterized in that: The imaging performance change estimating unit estimates a change amount of a position of an imaging point of the imaging optical system from before the start of processing as the estimated imaging performance change amount.

3. The laser processing device according to claim 1 or 2, characterized in that: The temperature estimating unit estimates the temperature of the optical component at a plurality of times in time series, and estimates the temperature of the optical component based on the temperature of the optical component at a time at least one step before the estimated time.

4. The laser processing device according to any one of claims 1 to 3, characterized in that: When the laser output value of the laser is less than a specific value during a specific time, the temperature estimating unit updates the temperature information measured by the temperature sensor to the latest temperature information, and estimates the estimated temperature based on the latest temperature information and the beam characteristics.

5. The laser processing device according to any one of claims 1 to 4, characterized in that: The method further comprises a correction coefficient determination unit that determines a correction coefficient for correcting the estimated imaging performance change amount based on processing type information indicating the type of the laser processing. The correction amount calculation unit corrects the estimated imaging performance change amount using the correction coefficient, and calculates the correction amount based on the corrected estimated imaging performance change amount.

6. The laser processing device according to claim 5, characterized in that: The processing type information includes at least one of the material of the workpiece, the thickness of the workpiece, and the type of processing gas used in the laser processing.

7. The laser processing device according to any one of claims 1 to 6, characterized in that: The temperature sensor is mounted on a gripping portion that grips the optical component.

8. The laser processing device according to any one of claims 1 to 7, characterized in that: The temperature estimation unit includes a first machine learning device, The first machine learning device comprises: a first data acquisition unit that acquires a first state quantity including first temperature information among the temperature information and a first beam characteristic among the beam characteristics; as well as The first learning unit learns the situation of estimating the estimated temperature based on the first state quantity, generates a first trained model, and estimates the estimated temperature corresponding to the second state quantity based on the second state quantity including the second temperature information in the temperature information and the second beam characteristic in the beam characteristic and the first trained model.

9. The laser processing device according to any one of claims 1 to 8, characterized in that: The thermal lens estimation unit includes a second machine learning device, The second machine learning device comprises: a second data acquisition unit that acquires a third state quantity including a first estimated temperature among the estimated temperatures; and A second learning unit learns the situation of estimating the thermal lens amount based on the third state quantity, generates a second trained model, and estimates the thermal lens amount corresponding to the fourth state quantity based on a fourth state quantity including a second estimated temperature among the estimated temperatures and the second trained model.

10. The laser processing device according to any one of claims 1 to 9, characterized in that: The imaging performance change estimation unit includes a third machine learning device, The third machine learning device comprises: a third data acquisition unit that acquires a fifth state amount including a first thermal lens amount among the thermal lens amounts; and The third learning unit learns the situation of estimating the estimated imaging performance change amount based on the fifth state quantity, generates a third trained model, and estimates the estimated imaging performance change amount corresponding to the sixth state quantity based on the sixth state quantity including the second thermal lens quantity among the thermal lens quantities and the third trained model.

11. The laser processing device according to any one of claims 1 to 10, characterized in that: The correction amount calculation unit includes a fourth machine learning device, The fourth machine learning device comprises: a fourth data acquisition unit that acquires a seventh state quantity including a first estimated imaging performance change quantity among the estimated imaging performance change quantities; and The 4th learning unit learns the situation of estimating the correction amount based on the 7th state quantity, generates the 4th trained model, and estimates the correction amount corresponding to the 8th state quantity based on the 8th state quantity including the 2nd estimated imaging performance change amount among the estimated imaging performance change amount and the 4th trained model.

12. A laser processing device, characterized in that: have: a data acquisition unit that acquires a first state quantity including a first output value of a laser beam irradiated to an optical component disposed in a processing head and first temperature information that is information on a temperature measured by a temperature sensor disposed in the processing head; a learning unit that learns the estimation of the correction amount of the processing parameter based on the first state amount, generates a trained model, and estimates the correction amount corresponding to the second state amount based on a second state amount including a second output value of the laser and second temperature information of the temperature measured by the temperature sensor and the trained model; and A control unit controls laser processing using the laser light and changes the processing parameter based on the correction amount during the laser processing.

13. A control device, characterized in that: have: a beam characteristic calculation unit that calculates the beam characteristic of the laser beam irradiated to the optical component disposed in the processing head; a temperature estimating unit that estimates an estimated temperature of the optical component based on temperature information, which is information on a temperature measured by a temperature sensor disposed in the processing head, and the beam characteristics; a thermal lens estimating unit that estimates a thermal lens amount of the optical component based on the estimated temperature; an imaging performance change estimating unit that estimates an estimated imaging performance change amount, which is an amount of change in imaging performance of the imaging optical system of the machining head from before machining starts, based on the thermal lens amount; a correction amount calculation unit that calculates a correction amount of a processing parameter based on the estimated imaging performance change amount; and A control unit controls laser processing using the laser light and changes the processing parameter based on the correction amount during the laser processing.

14. A laser processing system, characterized in that: have: a laser processing unit that irradiates a workpiece with laser light from a processing head provided with an optical component to perform laser processing on the workpiece; and a processing control unit, which controls the laser processing unit, The laser processing unit has: a laser oscillator that oscillates the laser light; and a temperature sensor disposed in the processing head to measure the temperature in the processing head; The processing control unit has: a beam characteristic calculation unit that calculates the beam characteristic of the laser beam irradiated to the optical component; a temperature estimating unit that estimates an estimated temperature of the optical component based on temperature information (ie, information on the temperature measured by the temperature sensor) and the light beam characteristics; a thermal lens estimating unit that estimates a thermal lens amount of the optical component based on the estimated temperature; an imaging performance change estimating unit that estimates an estimated imaging performance change amount, which is an amount of change in imaging performance of the imaging optical system of the machining head from before machining starts, based on the thermal lens amount; a correction amount calculation unit that calculates a correction amount of a processing parameter based on the estimated imaging performance change amount; and A control unit controls the laser processing using the laser light and changes the processing parameter based on the correction amount during the laser processing.

15. A laser processing method, characterized in that: Include: a laser processing step in which a laser processing unit irradiates a workpiece with laser light from a processing head provided with an optical component to perform laser processing on the workpiece; and a processing control step, wherein the processing control unit controls the laser processing unit, The laser processing steps include: a laser oscillation step of oscillating the laser light by a laser oscillator; and a temperature measuring step, wherein a temperature sensor disposed in the processing head measures the temperature in the processing head; The process control step comprises: a beam characteristic calculation step, wherein the processing control unit calculates the beam characteristic of the laser beam irradiated to the optical component; a temperature estimating step in which the process control unit estimates the estimated temperature of the optical component based on the temperature information measured by the temperature sensor, i.e., the temperature information and the beam characteristics; a thermal lens estimating step, wherein the process control unit estimates a thermal lens amount of the optical component based on the estimated temperature; an imaging performance change estimating step, wherein the processing control unit estimates an estimated imaging performance change amount, which is an amount of change in imaging performance of the imaging optical system of the processing head from before the start of processing, based on the thermal lens amount; a correction amount calculation step, wherein the processing control unit calculates the correction amount of the processing parameter based on the estimated imaging performance change amount; as well as In the control step, the process control unit controls the laser process using the laser light, and changes the process parameter based on the correction amount during the laser process.