Laser device, laser processing device, learning device, inference device, laser processing system and laser processing method

Abstract

The laser device (500) is characterized in that it comprises: a Q-switched laser oscillator (100) that generates pulsed laser light; an amplifier (200) that amplifies the pulsed laser light; an optical switch element (26) that is arranged on an optical path between the Q-switched laser oscillator (100) and the amplifier (200); and a control device (35) that modulates the transmittance of the optical switch element (26) based on a pulse characteristic time that represents a characteristic of a time interval at which the Q-switched laser oscillator (100) generates pulsed laser light.

Description

Technical Field

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

[0002] When a high-output pulse laser is required, the following structure is adopted, that is, after a pulse laser with a lower output than the required laser output is generated, the pulse laser is amplified by an amplifier. In the above structure, when the time interval for generating the pulse laser, that is, the pulse period, is not constant, the time interval for injecting the pulse laser into the amplifier will change, and since the gain of the amplifier changes for each pulse laser, the pulse energy of the pulse laser output from the amplifier will fluctuate.

[0003] Patent document 1 discloses a pulse laser system, which, when a pulse laser with an irregular pulse period is amplified by an amplifier, injects a secondary signal having a wavelength different from the main signal into the amplifier in addition to the main signal, thereby suppressing the change in the time interval of injecting the pulse laser into the amplifier and suppressing the change in the gain of the amplifier. In this pulse laser system, the secondary signal is removed from the output of the amplifier and the main signal is taken out as laser output.

[0004] Patent Document 1: Japanese Patent Application No. 2018-531524 Summary of the invention

[0005] However, according to the above-mentioned prior art, when the desired pulse period is long, the number of secondary signals to be removed after amplification increases, so that most of the input power is not used for the main signal but for the secondary signal, resulting in a problem of reduced energy efficiency.

[0006] The present invention has been made in view of the above circumstances, and its object is to obtain a laser device that can suppress a decrease in conversion efficiency from input power to laser output and suppress fluctuations in amplified pulse energy even when the pulse period varies.

[0007] In order to solve the above-mentioned problems and achieve the purpose, the laser device of the present invention is characterized in that it has: a Q-switched laser oscillator, which generates pulsed laser; an amplifier, which amplifies the pulsed laser; an optical switch element, which is arranged on the optical path between the Q-switched laser oscillator and the amplifier; and a control device, which modulates the transmittance of the optical switch element based on a pulse characteristic time that represents the characteristics of the time interval for the Q-switched laser oscillator to generate pulsed laser.

[0008] Effects of the Invention

[0009] According to the present invention, there is an effect of obtaining a laser device capable of suppressing a decrease in conversion efficiency from input power to laser output and suppressing fluctuations in amplified pulse energy even when a pulse period varies. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a diagram showing the structure of the laser device according to the first embodiment.

[0011] Figure 2 This is a diagram showing an example of a detailed structure of the laser device according to the first embodiment.

[0012] Figure 3 This is a diagram showing the configuration of a laser processing apparatus using the laser device according to Embodiment 1 as a laser light source.

[0013] Figure 4 FIG. 1 is a diagram showing an example of a target shape of a hole formed in an electronic substrate.

[0014] Figure 5 This is a diagram showing an example of a pattern of processing holes and a processing path to be processed on an electronic substrate.

[0015] Figure 6 Yes Figure 5 FIG. 1 is a diagram showing the time change of the waveform of the pulsed laser when machining holes of the pattern shown.

[0016] Figure 7 This is a diagram illustrating the effect of the laser device.

[0017] Figure 8 This is a flowchart for explaining the control operation of the laser processing device involved in the second embodiment.

[0018] Fig. 9 This is a flowchart for explaining the control operation of the laser processing device involved in the third embodiment.

[0019] Fig.10 This is a diagram showing the structure of a learning device according to a fourth embodiment.

[0020] Fig.11 is a diagram showing an example of a 3-layer neural network.

[0021] Fig.12 This is a flowchart for explaining the learning process of the learning device.

[0022] Fig.13 This is a structural diagram of an inference device related to a laser device.

[0023] Fig.14This is a flowchart for explaining a process for obtaining the transmittance using the estimation device.

[0024] Fig.15 This is a diagram showing the structure of a learning device according to the fifth embodiment.

[0025] Fig.16 This is a structural diagram of an inferred device related to a laser processing device.

[0026] Fig.17 This is a diagram showing an example of the waveform of pulsed laser light having different pulse intervals.

[0027] Fig.18 This is an explanatory diagram of an example in which the transmittance is changed over time within the pulse time.

[0028] Fig.19 This is an explanatory diagram related to the control of transmittance involved in the seventh embodiment.

[0029] Fig. 20 This is a diagram showing a partial structure between electrodes of a laser device according to an eighth embodiment.

[0030] Fig.21 Yes means Fig. 20 A diagram showing steady-state gain distribution between electrodes of a laser device having the structure shown.

[0031] Fig. 22 This is a diagram showing the internal structure of the laser device involved in Embodiment 9.

[0032] Fig.23 This is a diagram showing the temperature distribution between electrodes of a laser device in a steady state.

[0033] Fig.24 This is a flowchart for explaining the operation of the laser processing device involved in embodiment 10. DETAILED DESCRIPTION

[0034] Hereinafter, a laser device, a laser processing device, a learning device, an inference 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 accompanying drawings.

[0035] Implementation method 1.

[0036] Figure 11 is a diagram showing a structure of a laser device 500 according to Embodiment 1. The laser device 500 includes: a Q-switched laser oscillator 100 that generates pulsed laser light using an element having a shutter function such as a Q switch; an amplifier 200 that amplifies the pulsed laser light generated by the Q-switched laser oscillator 100; an optical switch element 26 that is disposed on an optical axis 2 between the Q-switched laser oscillator 100 and the amplifier 200; a control device 35; and an information processing device 36.

[0037] The pulse laser generated by the Q-switched laser oscillator 100 is incident on the optical switch element 26, and after passing through the optical switch element 26 at a set transmittance, it is incident on the amplifier 200 along the optical axis 2. The transmittance of the optical switch element 26 is modulated according to a signal from the control device 35. In addition, "modulating the transmittance" means changing the transmittance over time. The optical switch element 26 is, for example, an acousto-optic element, an electro-optic element, etc.

[0038] The control device 35 controls the time interval for the Q-switched laser oscillator 100 to oscillate pulsed laser light, namely, the pulse cycle, the pulse width, and the power input to the Q-switched laser oscillator 100 and the amplifier 200 in parallel with the control of the transmittance of the optical switch element 26 .

[0039] The information processing device 36 calculates a control signal of the optical switch element corresponding to the oscillation interval of the pulsed laser based on information obtained by sensors (not shown) provided in the Q-switched laser oscillator 100 and the amplifier 200 , and transmits information including the calculation result to the control device 35 .

[0040] The information acquired by the sensor includes, for example, pulse energy of pulsed laser, waveform of pulsed laser, temperature information of laser device 500, etc. Based on the information from information processing device 36, control device 35 sends a control signal to optical switch element 26, etc., thereby controlling the operation of laser device 500.

[0041] The pulse laser light transmitted through the optical switch element 26 and incident on the amplifier 200 is amplified by the amplifier 200 and then emitted along the optical axis 3. The optical switch element 26 is controlled so that the fluctuation of the pulse energy of the pulse laser light after being emitted from the amplifier 200 becomes small when the pulse laser light is continuously generated. Figure 1 In the figure, the laser device 500 includes one optical switch element 26 , but the laser device 500 may include a plurality of optical switch elements 26 .

[0042] In addition, Figure 1 , the Q-switched laser oscillator 100 and the amplifier 200 are shown as separate devices, but as described below, the Q-switched laser oscillator 100 and the amplifier 200 may be a single device configured in a single housing.

[0043] The functions of the control device 35 and the information processing device 36 are implemented using processing circuits. These processing circuits may be implemented by dedicated hardware or may be control circuits using a CPU (Central Processing Unit).

[0044] When the processing circuit is dedicated hardware, 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 is used.

[0045] When the processing circuit is implemented by a control circuit using a CPU, the control circuit has a processor and a memory. The processor is also called a CPU, a processing device, an arithmetic device, a microprocessor, a microcomputer, a DSP (Digital Signal Processor), etc. The memory is, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (registered trademark) (Electrically EPROM), a magnetic disk, a floppy disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disk), etc.

[0046] When the processing circuit is realized by a control circuit using a CPU, the processor reads out and executes a program stored in the memory corresponding to the processing of the control device 35 and the information processing device 36. The memory is also used as a temporary memory in each process executed by the processor.

[0047] Figure 2 FIG. 1 is a diagram showing an example of a detailed structure of a laser device 500 according to Embodiment 1. Figure 2 , the internal structure of the laser device 500 is shown in a perspective view. The laser device 500 is, for example, a three-axis orthogonal carbon dioxide gas laser. Alternatively, the laser device 500 may be a carbon monoxide laser, an excimer laser, or the like.

[0048] exist Figure 2 In the structure shown, Figure 1 The Q-switched laser oscillator 100 and the amplifier 200 of the laser device 500 shown are housed in the same housing 300 .

[0049] Laser gas is sealed in the frame 300. The laser device 500 has blowers 40, 41, a pair of electrodes 11 and a pair of electrodes 12, and heat exchangers 42, 43 in the frame 300. The laser gas flows in the air flow directions 13, 14 indicated by the arrows through the blowers 40, 41. The laser gas then passes between the electrodes 11, 12. High-frequency power is applied to the electrodes 11, 12 according to the control of the discharge control device 44, and silent discharge is generated between the electrodes. The laser gas is excited by this discharge. Then, the laser gas flows in the air flow directions 15, 16 indicated by the arrows and is cooled by the heat exchangers 42, 43.

[0050] In addition, the laser device 500 has a total reflection mirror 21 and a partial reflection mirror 24. The total reflection mirror 21 and the partial reflection mirror 24 constitute a resonator, and the total reflection mirror 21 and the partial reflection mirror 24 are arranged in such a manner that the optical axis 1 of the resonator is located in the discharge space where the laser gas is excited. However, in order to keep the laser gas excited for a certain period of time after passing through the discharge space, the optical axis 1 may pass through a position deviated from the discharge space.

[0051] The laser device 500 further includes a Q switch 22. The Q switch 22 is disposed on the optical axis 1 of the resonator, and controls the Q value of the resonator to generate pulse oscillation and generate pulse laser light. The Q switch 22 may be, for example, an acousto-optic element or an electro-optic element.

[0052] The total reflection mirror 21 constituting the resonator reflects almost all the light, but transmits a small amount of light, and a light sensor 50 is arranged at the position where the transmitted light enters. The light sensor 50 measures the pulse waveform and pulse energy of the pulse laser oscillated by the resonator. The laser device 500 also has a window 23 that cuts off the laser gas in the housing 300 from the outside air. Figure 2 In the example shown, the total reflection mirror 21, the Q switch 22, and the optical sensor 50 are arranged outside the housing 300, and the window 23 prevents the laser gas from leaking out of the housing 300, and allows the light from the partial reflection mirror 24 to pass toward the total reflection mirror 21 and to the outside of the housing 300. The partial reflection mirror 24 also has a function of cutting off the laser gas in the housing 300 from the external gas. The elements arranged between the optical sensor 50 and the partial reflection mirror 24 along the optical axis 1 constitute the Q-switched laser oscillator 100.

[0053] In the above description, the Q switch 22 is disposed in the atmosphere, but the Q switch 22 may be disposed in the housing 300, and the laser gas in the housing 300 and the external gas may be cut off by the total reflection mirror 21 instead of the window 23. In addition, one or more mirrors may be disposed between the window 23 and the total reflection mirror 21.

[0054] The pulse laser emitted from the partial reflection mirror 24 of the oscillator is incident on the optical switch elements 26 and 27 via the mirror 25, and the pulse laser transmitted by the optical switch elements 26 and 27 is incident again into the frame 300 from the window 29 along the optical axis 2 via the mirror 28. At this time, the beam diameter of the pulse laser can be adjusted using a lens, a curvature mirror, etc. on the optical path from the partial reflection mirror 24 of the resonator to the window 29. The pulse laser incident into the frame from the window 29 is amplified by passing through the excited laser gas, reflected by the mirror 30, and incident again into the excited laser gas. Then, after passing through the excited laser gas and being amplified, it is reflected by the mirror 31 and incident again into the excited laser gas. Then, after passing through the excited laser gas and being amplified, it is reflected by the mirror 32 and incident again into the excited laser gas. Then, after passing through the excited laser gas and being amplified, the amplified pulse laser is output to the outside of the frame 300 from the window 33. The amplified pulsed laser light is reflected by the partial reflection mirror 34 along the optical axis 3 and output as laser output. A part of the light transmitted by the partial reflection mirror 34 is incident on the optical sensor 51. The optical sensor 51 measures the pulse waveform, pulse energy, etc. of the pulsed laser light output as laser output.

[0055] Until the pulse laser light incident into the housing through the window 29 passes through the excited laser gas in the housing 300 and is output from the partial reflection mirror 34 , the portion including the optical sensor 51 constitutes the amplifier 200 .

[0056] Figure 2 The laser device 500 shown has an integrated MOPA (Master Oscillator Power Amplifier) ​​structure, that is, the Q-switched laser oscillator 100 and the amplifier 200 are arranged in a frame 300, and the optical axes of the Q-switched laser oscillator 100 and the amplifier 200 pass through at least one continuous discharge space. Here, an aperture (not shown) can be arranged between the reflection surface of each mirror in the frame 300 and the discharge space to limit the range where light passes.

[0057] The laser device 500 can discharge continuously and perform pulse oscillation by rapidly changing the Q value of the resonator using the Q switch 22 .

[0058] The control device 35 is connected to the Q switch 22 , the optical switch elements 26 , 27 , and the discharge control device 44 , and controls them.

[0059] The information processing device 36 receives information from the optical sensors 50 and 51. The information processing device 36 may also receive control signals of the optical switch elements 26 and 27 and control signals of the discharge current from the control device 35. The information processing device 36 may calculate the pulse energy of the pulse laser based on the pulse waveform of the pulse laser.

[0060] In addition, the information processing device 36 can receive information indicating the state of the laser device 500, such as the temperature of the laser gas, the gas pressure, the temperature of the laser device 500, the temperature of the cooling water, and other information that changes over time from sensors not shown. In addition, as described below, when the laser device 500 is used as a laser light source of a laser processing device, information indicating the timing of laser oscillation, the setting time, the stationary time, and the positioning time including the setting time and the stationary time of the electrically controlled mirror mounted on the laser processing device can be received from the laser processing device.

[0061] The information processing device 36 calculates information necessary for controlling the Q switch 22 , the optical switch elements 26 and 27 , and the discharge control device 44 based on the received information, and transmits the information to the control device 35 .

[0062] Figure 3 1 is a diagram showing the structure of a laser processing device 510 using the laser device 500 according to Embodiment 1 as a laser light source. The laser processing device 510 includes the laser device 500 and a hole processing machine 400. The hole processing machine 400 is a device that performs hole processing using a pulsed laser output by the laser device 500, and can perform hole processing on an electronic substrate, for example. The hole processing machine 400 is positioned using a positioning mechanism such as an electrically controlled mirror 403 so that the pulsed laser is irradiated to a predetermined position of the electronic substrate.

[0063] The pulse laser output by the laser device 500 is incident on the drilling machine 400. The pulse laser is irradiated to the electrically controlled mirror 403 via the mirrors 401 and 402 of the drilling machine 400. The electrically controlled mirror 403 is an example of a deflection element that deflects the pulse laser, thereby adjusting the irradiation position of the pulse laser on the processing object 405. In addition, in the optical path from the time when the pulse laser is incident on the drilling machine 400 to the time when it is irradiated on the electrically controlled mirror 403, optical elements such as lenses and spherical mirrors (not shown) for adjusting the beam diameter may be arranged, and a mask for shaping the beam profile may also be arranged. In addition, in Figure 3 Although one galvano-controlled mirror 403 is shown in the figure, two galvano-controlled mirrors 403 may be used to form a two-axis structure so that a plane can be scanned.

[0064] The pulse laser irradiated to the electrically controlled mirror 403 is irradiated onto the processing object 405 via the lens 404 as the objective optical system. When the above-mentioned mask is used, it can be a transfer optical system that transfers the pulse laser formed by the mask to the processing object 405. The processing object 405 can be set on a worktable movable in three orthogonal axis directions.

[0065] By adjusting the angle of the galvano-mirror 403 , the position on the object 405 to be processed is positioned to be irradiated with the pulse laser.

[0066] The pulse laser is irradiated once or more at the position positioned by the galvano-controlled mirror 403, and then the next pulse laser is irradiated after positioning at another position by the galvano-controlled mirror 403. By repeatedly and continuously performing the above-mentioned process, many holes are processed in the processing object 405.

[0067] The time required for the galvano-mirror 403 to perform positioning depends on the target shape of the hole to be processed in the electronic substrate, that is, the processing pattern of the hole. Figure 4 FIG. 1 is a diagram showing an example of a target shape of a hole formed in an electronic substrate. Figure 4 The arrows indicate the processing paths of the holes. In the following description, each processing path is identified by the numbers attached to the processing paths. When the holes are processed in the order of processing path #1, processing path #2, processing path #3, etc., the time taken for the electric-controlled mirror 403 to position becomes shorter in the parts of the electronic substrate where the holes are spaced short, such as processing path #1, processing path #4, processing path #6, processing path #7, etc., and the time taken for the electric-controlled mirror 403 to position becomes longer in the parts where the holes are spaced far apart, such as processing path #3, processing path #5, processing path #8, etc. Therefore, when a plurality of holes are continuously opened in the electronic substrate, the positioning time of the electric-controlled mirror when processing each hole is not constant and varies in time.

[0068] The pulse laser is irradiated at the timing when the positioning of the electrically controlled reflector 403 is completed, so the timing of emitting the pulse laser from the laser device 500 also varies in time. In Q-switched oscillation, if the oscillation timing of the pulse laser varies in time, the accumulated time of the gain varies for each pulse laser, so the pulse energy of the oscillating pulse laser also varies in time. Therefore, if the pulse laser oscillated by the Q-switched laser oscillator 100 is directly amplified by the amplifier 200, the pulse energy of the pulse laser also varies in time. In this case, in the hole processing machine 400, the pulse energy of the pulse laser varies for each processing hole. This situation is applied to Figure 5 and Figure 6 Shown.

[0069] Figure 5 This is a diagram showing an example of a pattern of processing holes and a processing path to be processed on an electronic substrate. Figure 6 Yes Figure 5 The figure shows the time variation of the waveform of the pulsed laser when machining the machining holes of the pattern shown. Figure 5 As shown in FIG. 1 , when hole processing is performed in the order of processing hole #1, processing hole #2, processing hole #3, and processing hole #4, the waveform of the pulse laser generated by Q-switch oscillation becomes as follows: Figure 6 shown. Figure 6 The horizontal axis represents time, and the numbers attached to the horizontal axis are Figure 5 The numbers attached to the processing holes correspond to the numbers. The hole intervals in processing holes #3 and #4 are longer than those in processing holes #1 and #2. Therefore, the pulse energy in processing holes #3 and #4 is higher than that of the pulse laser irradiated when processing processing holes #1 and #2. In this case, the pulse energy of the pulse laser used in processing fluctuates for each processing hole, so the processing quality may be unstable.

[0070] Therefore, in the laser device 500, in order to suppress the fluctuation of the pulse energy of each pulse laser incident on the hole processing machine 400, the transmittance of the pulse laser emitted from the Q-switched laser oscillator 100 when passing through the optical switch element 26 is adjusted for each pulse laser, so as to suppress the fluctuation of the pulse energy of the pulse laser incident on the amplifier 200.

[0071] Figure 7 It is an explanatory diagram of the effect of the laser device 500 . Figure 7 (a) shows the waveform of the pulse laser oscillated by the Q-switched laser oscillator 100 . Figure 7 (b) shows the transmittance of the optical switch element 26 . Figure 7 (c) shows the waveform of the pulse laser input to the amplifier 200 . Figure 7 (d) shows the waveform of the pulse laser output from the amplifier 200 .

[0072] The oscillation timing in the Q-switched laser oscillator 100 is not a constant cycle. When the pulse cycle changes, the longer the time interval from the previous oscillation timing, the greater the pulse energy of the pulse laser output from the Q-switched laser oscillator 100. For example, the length of the interval of the previous pulse laser is, in descending order, pulse laser #3, pulse laser #4, and pulse laser #1. In the case that the same as pulse laser #1 and pulse laser #2, the pulse energy of the pulse laser output from the Q-switched laser oscillator 100 is, in descending order, pulse laser #3, pulse laser #4, and pulse laser #1, which is the same as pulse laser #1 and pulse laser #2.

[0073] In addition, in the amplifier 200, when a pulse laser with the same pulse energy is input, the longer the time interval between the pulse laser and the previous pulse laser, the greater the pulse energy of the output pulse laser. Therefore, the longer the time interval between the pulse lasers, the smaller the transmittance of the optical switch element 26 is controlled, so that the longer the time interval between the pulse lasers, the smaller the pulse energy of the pulse laser input to the amplifier 200. Figure 7 In the example, the pulse energies of the pulse lasers injected into the amplifier 200 are in the order of pulse laser #3, pulse laser #4, and pulse laser #1 in ascending order, and the pulse laser #1 and the pulse laser #2 are the same, and the transmittances are in the order of pulse laser #3, pulse laser #4, and pulse laser #1 in ascending order, and the pulse laser #1 and the pulse laser #2 are the same. As a result, the pulse energy of the pulse lasers emitted from the amplifier 200 is close to uniform, and fluctuations are suppressed.

[0074] The time interval between pulsed lasers can be detected based on the pulse waveform, for example, and the transmittance can be controlled using the detected value. The generation time of the pulsed laser can be determined based on the measured voltage of a sensor such as a photodetector or a phototube that can measure the time dependence of the light intensity of the pulsed laser, and the time interval between the pulsed lasers can be defined according to the characteristic shape of the pulse waveform. For example, the peak moment of the pulse can be set as the generation time, the moment when the light intensity rises to a predetermined ratio relative to the peak value of the pulse can be set as the generation time, and the moment when the light intensity decreases to a predetermined ratio relative to the peak value after the pulse rises to the peak value can be set as the generation time.

[0075] The laser device 500 modulates the transmittance of the optical switch element 26 for each laser pulse based on the pulse characteristic time that indicates the characteristics of the time intervals at which the Q-switched laser oscillator 100 generates laser pulses. The pulse characteristic time may be, for example, the time interval between a plurality of laser pulses generated by the Q-switched laser oscillator 100, or a moving average of the time intervals between a plurality of laser pulses generated by the Q-switched laser oscillator 100. As the laser device 500, the transmittance is increased as the time interval indicated by the pulse characteristic time is shorter, and the transmittance of the optical switch element 26 is controlled so that the variation in energy between laser pulses is less than a predetermined value.

[0076] In addition, if Figure 2 As shown, when the laser device 500 includes a plurality of optical switch elements 26 and 27 , the laser device 500 performs control so that the transmittance of the plurality of optical switch elements 26 and 27 combined satisfies the above-mentioned condition.

[0077] As described above, the laser device 500 according to the first embodiment includes: the Q-switched laser oscillator 100 that generates pulsed laser light; the amplifier 200 that amplifies the pulsed laser light; the optical switch element 26 that is disposed on the optical path between the Q-switched laser oscillator 100 and the amplifier 200; and the control device 35 that modulates the transmittance of the optical switch element 26 based on the pulse characteristic time that indicates the characteristics of the time interval at which the Q-switched laser oscillator 100 generates pulsed laser light. Modulating the transmittance means changing the value of the transmittance over time. Specifically, in the first embodiment, the control device 35 changes the value of the transmittance for each pulsed laser light incident on the optical switch element 26. Thus, even when the time interval at which the Q-switched laser oscillator 100 generates pulsed laser light changes, the pulse energy of the pulsed laser light generated by the Q-switched laser oscillator 100 differs for each pulsed laser light, and the amplification factor of the amplifier 200 changes, the change in the pulse energy after amplification can be suppressed. In addition, in this case, in a method of suppressing the change in the time interval of injecting the pulsed laser into the amplifier by injecting the secondary signal into the amplifier in addition to the main signal, the decrease in the conversion efficiency from the input power to the laser output caused by removing the secondary signal and extracting the main signal as the laser output is suppressed. Therefore, the decrease in the conversion efficiency from the input power to the laser output can be suppressed, and even when the pulse period changes, the change in the pulse energy after amplification can be suppressed.

[0078] In addition, the control device 35 obtains the time interval between the multiple pulse lasers generated by the Q-switched laser oscillator 100, or the moving average of the time interval between the multiple pulse lasers generated by the Q-switched laser oscillator 100, as the pulse characteristic time. The shorter the time interval, the higher the transmittance of the optical switch element 26. The transmittance of the optical switch element 26 is controlled so that the energy variation between the multiple pulse lasers emitted from the amplifier 200 is less than a predetermined value. Here, the energy variation between the multiple pulse lasers emitted from the amplifier 200 is less than a predetermined value, for example, Figure 7 In the example, it means to control so that Figure 7 The difference in pulse energy between the pulse lasers #1 to #4 shown in (d) is smaller than a predetermined value. This can suppress a decrease in conversion efficiency from input power to laser output, and even when the pulse period changes, it is possible to suppress variations in the amplified pulse energy.

[0079] In the above description, the pulse laser is set to be irradiated at the timing when the positioning of the galvano-controlled mirror 403 is completed. However, it is also conceivable that when the positioning time of the galvano-controlled mirror 403 is too short, the gain accumulated during the period when the Q-switched laser oscillator 100 stops oscillating is too small, and the pulse energy of the pulse laser output from the amplifier 200 is less than the desired value. In this case, the following control can be performed, that is, the galvano-controlled mirror 403 is stopped until the desired pulse energy is obtained after amplification, and the pulse laser is irradiated at the time when the desired pulse energy is obtained.

[0080] Implementation method 2.

[0081] In the second embodiment, a control flow of a laser processing device 510 using the laser output of a laser device 500 in a hole drilling machine 400 for an electronic substrate will be described.

[0082] Figure 8 This is a flowchart for explaining the control operation of the laser processing device 510 according to Embodiment 2. The control device 35 of the laser device 500 first obtains data representing the hole pattern of the electronic substrate to be processed by the hole processing machine 400 (step S101). For example, the data representing the hole pattern may include position information of the holes of the electronic substrate to be processed.

[0083] Next, the control device 35 calculates the hole-drilling path of the electronic substrate based on the acquired data representing the hole-drilling pattern (step S102). Then, the control device 35 calculates the time interval for generating pulsed laser light by the Q-switched laser oscillator 100 to drill each drilled hole, that is, the oscillation interval of the pulsed laser light (step S103).

[0084] The control device 35 calculates the initial value of the transmittance of the optical switch element 26 for each laser pulse corresponding to the oscillation interval of the laser pulse (step S104). The control device 35 stores the calculated data of the oscillation interval of the laser pulse and the transmittance of the optical switch element 26 in, for example, a memory in the control device 35, and sets the transmittance of the optical switch element 26 for each laser pulse (step S105).

[0085] The control device 35 controls the Q-switched laser oscillator 100 and the optical switch element 26 using the calculated oscillation interval of the pulsed laser and the calculated transmittance of the optical switch element 26, and causes the Q-switched laser oscillator 100 to oscillate laser light (step S106).

[0086] In addition, the control device 35 obtains the pulse energy of the amplified pulse laser obtained by the optical sensor 51 via the information processing device 36 (step S107). In addition, the number of times the laser oscillation is performed in step S106 may be the same as the number of holes corresponding to one electronic substrate, or one electronic substrate may be divided into multiple times. The oscillated pulse laser is not irradiated to the electronic substrate, and the hole opening process is not performed yet.

[0087] The control device 35 determines whether the value indicating the fluctuation of the pulse energy of the amplified plurality of pulse lasers obtained in step S107 is less than or equal to the threshold value (step S108). When the fluctuation of the pulse energy is not less than or equal to the threshold value (step S108: No), the control device 35 corrects the transmittance of the optical switch element 26 when the pulse laser oscillates with the fluctuation of the pulse energy being greater than or equal to the threshold value based on the fluctuation of the pulse energy of each amplified pulse laser (step S109), and returns to the process of step S105. Therefore, the laser device 500 sets the corrected transmittance, and performs laser oscillation again while controlling the optical switch element 26 using the corrected transmittance, thereby obtaining the amplified pulse energy.

[0088] When the fluctuation of the pulse energy is less than or equal to the threshold value (step S108: Yes), the laser processing device 510 starts the hole drilling process of the electronic substrate (step S110). By performing the above-mentioned process, the laser device 500 repeats the correction of the transmittance of the optical switch element 26 until the fluctuation of the amplified pulse energy measured by laser oscillation is less than or equal to the threshold value.

[0089] The control device 35 can correct the transmittance using, for example, PID (Proportional Integral Differential) control, etc. Alternatively, the transmittance may be determined by machine learning as described later.

[0090] When it is known in advance that the fluctuation of the pulse energy is within a predetermined range by the value set as the initial value of the transmittance of the optical switch element 26, the processing such as the acquisition of the pulse energy and the correction of the fluctuation of the pulse energy can be omitted and the processing can be directly performed. That is, feedback control is not required during processing. In addition, the acquisition of the pulse energy and the correction of the fluctuation of the pulse energy can be performed while the processing is performed, that is, feedback control can be performed.

[0091] In addition, the sharing of the functions of the control device 35 and the information processing device 36 is an example, and the processing described as the function of the control device 35 in the above may be performed by the information processing device 36, or the processing described as the function of the information processing device 36 may be performed by the control device 35. For example, the acquisition of the data of the opening pattern of the electronic substrate, the calculation of the opening path of the electronic substrate, the calculation of the oscillation interval of the pulsed laser, the calculation of the initial value of the transmittance of the optical switch element 26, the calculation of the value indicating the fluctuation of the pulse energy, the calculation of the correction amount of the transmittance of the optical switch element 26, etc. may be performed by the information processing device 36.

[0092] As described above, the laser processing method involved in embodiment 2 includes the following steps: the control device 35 generates a pulsed laser by controlling the Q-switched laser oscillator 100; the control device 35 sets the transmittance of the optical switch element 26 that allows the pulsed laser to pass through; the pulse energy of the pulsed laser is changed by irradiating the pulsed laser to the optical switch element 26 with the set transmittance; the pulsed laser is amplified by the amplifier 200; the electrically controlled reflector 403 deflects the amplified pulsed laser to adjust the position where the pulsed laser is irradiated to the processing object 405; and the deflected pulsed laser is focused or transferred to irradiate the processing object 405. In the step of changing the pulse energy of the pulsed laser, the transmittance of the optical switch element 26 is modulated based on the pulse characteristic time that represents the characteristics of the time interval for generating the pulsed laser.

[0093] Implementation method 3.

[0094] In the second embodiment, control is performed so that fluctuations in the pulse energy of the pulse laser fall within a predetermined range, but control may be performed so that fluctuations in the shape of the processed hole fall within a predetermined range.

[0095] Fig. 9 1 is a flowchart for explaining the control operation of the laser processing device 510 according to Embodiment 3. The processing of Steps S101 to S106 is similar to that of Figure 8 The same, so the description is omitted here.

[0096] If laser oscillation occurs in step S106, the laser processing device 510 uses the pulsed laser output by the laser device 500 to start the hole drilling process of the electronic substrate (step S121). After the hole drilling process, the laser processing device 510 obtains the shape of the processed hole (step S122). The shape of the processed hole can be obtained, for example, by using an image obtained by using a camera, or by scanning the processing surface using a distance sensor that detects laser. The number of times the pulsed laser oscillates can be the same as the number of holes corresponding to one electronic substrate, or one electronic substrate can be divided into multiple times.

[0097] The control device 35 calculates a value indicating the fluctuation in the shape of the machined hole, and determines whether the fluctuation in the shape of the machined hole is within a predetermined range (step S123 ).

[0098] Here, the fluctuation of the shape of the processed hole is the width of the variation of the value representing the characteristics of each of the multiple processed holes. The value representing the characteristics of the processed hole can be a value representing the measurement result obtained by measuring each of the multiple processed holes, or a value calculated based on the measurement result. As an example of a value representing the characteristics of the processed hole, the hole diameter, the aspect ratio of the hole, the area of ​​the hole, the depth of the hole, the concave-convex bottom surface of the hole, the amount of scattered objects around the hole, etc. can be cited. In addition, the shape of the processed hole is not only specified with respect to the shape of the individual hole, but can also be recorded in the processing program, instructions, etc. with respect to the configuration of the hole, that is, how many holes are configured at which position, etc. In addition, it is also possible to specify the positional relationship between multiple processed holes.

[0099] When the fluctuation of the shape of the processed hole is not within the predetermined range (step S123: No), the control device 35 corrects the transmittance of the optical switch element 26 according to the fluctuation of the shape of the processed hole (step S124), and returns to the process of step S105. Here, the transmittance is set corresponding to each pulsed laser, but the transmittance to be corrected is the transmittance corresponding to the pulsed laser for processing the processing hole whose difference from the reference value representing the shape of the processed hole is not within the predetermined range.

[0100] When the fluctuation of the processed hole shape is within a predetermined range (step S123: Yes), the electronic substrate is drilled at the set transmittance (step S125). Before the transmittance used for drilling is determined, an electronic substrate sample for adjustment can be used.

[0101] The control device 35 can correct the transmittance using, for example, PID control, etc. Alternatively, the transmittance may be determined by machine learning as described later.

[0102] In the third embodiment, the sharing of the functions of the control device 35 and the information processing device 36 is also an example, and the processing described as the function of the control device 35 in the above may be performed by the information processing device 36, or the processing described as the function of the information processing device 36 may be performed by the control device 35. For example, the acquisition of the data of the opening pattern of the electronic substrate, the calculation of the opening path of the electronic substrate, the calculation of the oscillation interval of the pulsed laser, the calculation of the initial value of the transmittance of the optical switch element 26, the acquisition of the processed hole shape, the calculation of the value indicating the fluctuation of the processed hole shape, the calculation of the correction amount of the transmittance of the optical switch element 26, etc. may be performed by the information processing device 36.

[0103] As described above, the laser processing device 510 according to the third embodiment includes: the laser device 500; the galvano-mirror 403, which is a deflection element that deflects the pulsed laser output from the amplifier 200; the lens 404, which is an objective optical system that focuses or transfers the pulsed laser from the galvano-mirror 403 and irradiates the processing object 405; and the moving mechanism that moves the processing object 405. The control device 35 controls the transmittance according to the processing hole characteristic value representing the characteristics of the processing hole included in the processing path when the processing object 405 is punched by the pulsed laser, and the transmittance is increased as the interval between the processing holes is shortened, and the transmittance is controlled so that the value representing the fluctuation of the shapes of the plurality of processing holes is smaller than a predetermined value. When the laser device 500 is used for hole opening processing, the longer the interval between the processed holes, the longer the pulse characteristic time becomes. Therefore, by controlling the transmittance in accordance with the characteristic value of the processed holes, the transmittance can be controlled based on the pulse characteristic time, and the shape of the processed holes can be homogenized.

[0104] Furthermore, the machined hole characteristic value is a value indicating the interval between a plurality of machined holes on the machining path, or a moving average of the interval between a plurality of machined holes.

[0105] Implementation method 4.

[0106] In embodiments 2 and 3, the case where the hole pattern of the electronic substrate is known in advance is shown, but when the number of holes in the electronic substrate is very large, the transmittance for each hole needs to be stored as data, which puts pressure on memory resources. In addition, the oscillation timing of the pulse laser also needs to be determined in advance.

[0107] In the fourth embodiment, a control method is shown which can be applied even when the hole pattern of the electronic substrate and the oscillation timing of the pulsed laser are not known in advance.

[0108] Fig.101 is a diagram showing a configuration of a learning device 60 according to Embodiment 4. The learning device 60 performs machine learning related to the laser device 500. The learning device 60 includes a learning data acquisition unit 61 that acquires learning data, which is data used for learning, and a model generation unit 62 that generates a trained model for estimating the transmittance of the optical switch element 26 using the learning data. The model generation unit 62 stores the generated trained model in the trained model storage unit 70.

[0109] The learning data acquisition unit 61 acquires state quantities including interval information indicating the time interval at which the laser device 500 generates pulsed laser light and the pulse energy after the pulsed laser light is amplified, and the transmittance of the optical switch element 26 as learning data. The interval information may be any information as long as it is information indicating the time interval at which the pulsed laser light is generated. The interval information is, for example, information including the pulse characteristic time, the energy of the pulsed laser light generated by the Q-switched laser oscillator 100, the waveform of the pulsed laser light generated by the Q-switched laser oscillator 100, the waveform of the pulsed laser light amplified by the amplifier 200, and at least one of the drive current or discharge current of the Q-switched laser oscillator 100 and the amplifier 200. For example, the learning device 60 acquires the pulse energy of the amplified pulsed laser light when the time interval at which the pulsed laser light is generated and the transmittance of the optical switch element 26 are changed to various values, and acquires state quantities including the interval information and the amplified pulse energy at this time and the set transmittance as learning data.

[0110] In addition, when the laser medium of the laser device 500 is a gas laser serving as a gas, the state quantity obtained by the learning data acquisition unit 61 may further include at least one of the cooling water temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas pressure of the Q-switched laser oscillator 100 or the amplifier 200, the continuous discharge time of the Q-switched laser oscillator 100 or the amplifier 200, the electrode temperature of the Q-switched laser oscillator 100 or the amplifier 200, and the total discharge time of the Q-switched laser oscillator 100 or the amplifier 200 from the time the optical components are replaced.

[0111] The model generation unit 62 learns the transmittance of the optical switch element 26 by creating learning data based on a combination of state quantities including the interval information output from the learning data acquisition unit 61 and the pulse energy after amplification of the pulse laser light generated by the laser device 500 and the transmittance of the optical switch element 26. Specifically, the model generation unit 62 generates a trained model for estimating the transmittance of the optical switch element 26 at which the amplified pulse energy becomes a target value based on the state quantity of the laser device 500. Here, the learning data is data in which the state quantity and the transmittance of the optical switch element 26 are associated with each other.

[0112] The learning algorithm used by the model generation unit 62 can use a known algorithm such as tutored learning, untutored learning, and reinforcement learning. As an example, a case where a neural network is applied will be described.

[0113] The model generation unit 62 learns the transmittance of the optical switch element 26 by so-called tutor learning, for example, according to the neural network model. Here, tutor learning refers to a method in which a data set of input and result (label) is given to the learning device 60, thereby learning the features in their learning data and inferring the result based on the input.

[0114] The neural network is composed of an input layer consisting of multiple neurons, a hidden layer consisting of multiple neurons, namely an intermediate layer, and an output layer consisting of multiple neurons. The intermediate layer can be 1 layer or more than 2 layers.

[0115] Fig.11 is a diagram showing an example of a 3-layer neural network. For example, if Fig.11 In the three-layer neural network shown in FIG. 1 , if multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). The output result changes according to the values ​​of weight W1 and weight W2.

[0116] In the fourth embodiment, the neural network learns the transmittance by so-called supervised learning according to the learning data created based on the combination of the state quantity and the transmittance acquired by the learning data acquisition unit 61 .

[0117] That is, the neural network learns by adjusting weights W1 and W2 so that a state quantity including a target value of the amplified pulse energy is input to the input layer, and a result output from the output layer is close to the transmittance of the optical switch element 26 such that the amplified pulse energy becomes the target value.

[0118] The model generation unit 62 generates a trained model by executing the above learning, and outputs the trained model to the trained model storage unit 70 .

[0119] The trained model storage unit 70 stores the trained model output from the model generation unit 62 .

[0120] Next, use Fig.12 , the processing learned by the learning device 60 is explained. Fig.12 This is a flowchart for explaining the learning process of the learning device 60 .

[0121] The learning data acquisition unit 61 acquires learning data including state quantities and transmittance (step S201). Although the state quantities and transmittance are acquired simultaneously here, the state quantities and transmittance may be acquired at different timings as long as they can be input in association with each other.

[0122] The model generation unit 62 performs a learning process to learn the transmittance so that the amplified pulse energy becomes a target value according to the learning data created based on the combination of the state quantity and transmittance obtained by the learning data acquisition unit 61, through so-called teacher learning, thereby generating a trained model (step S202).

[0123] The trained model storage unit 70 stores the trained model generated by the model generation unit 62 (step S203 ).

[0124] Fig.13 1 is a block diagram of an estimation device 80 related to the laser device 500. The estimation device 80 includes an estimation data acquisition unit 81 and an estimation unit 82.

[0125] The inference data acquisition unit 81 acquires state quantities as inference data. The state quantities include the above-mentioned interval information and the target value of the amplified pulse energy. In addition, when the laser medium of the laser device 500 is a gas laser as a gas, the state quantities acquired by the inference data acquisition unit 81 may further include at least one of the cooling water temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas pressure of the Q-switched laser oscillator 100 or the amplifier 200, the continuous discharge time of the Q-switched laser oscillator 100 or the amplifier 200, the electrode temperature of the Q-switched laser oscillator 100 or the amplifier 200, and the total discharge time of the Q-switched laser oscillator 100 or the amplifier 200 from the time of replacement of the optical component.

[0126] The inference unit 82 infers the transmittance obtained using the trained model. That is, the inference unit 82 inputs the inference data acquired by the inference data acquisition unit 81 to the trained model stored in the trained model storage unit 70, thereby being able to output the transmittance estimated from the state quantity so that the amplified pulse energy becomes the target value.

[0127] In addition, the trained model used by the inference device 80 may be a trained model learned by using learning data obtained from the laser device 500 that is the inference object of the inference device 80, and may be a trained model obtained from outside such as other laser devices 500 that are different from the laser device 500 that is the inference object of the inference device 80 and used.

[0128] Next, use Fig.14 , the processing for obtaining the transmittance using the estimation device 80 is described. Fig.14 This is a flowchart for explaining a process for obtaining the transmittance using the estimation device 80 .

[0129] The estimation data acquisition unit 81 acquires estimation data (step S301 ).

[0130] The estimation unit 82 inputs the state quantity to the trained model stored in the trained model storage unit 70 (step S302 ), and outputs the estimation result of the transmittance to the laser device 500 (step S303 ).

[0131] The laser device 500 controls the optical switch element 26 using the estimated result of the output transmittance (step S304 ).

[0132] For example, in Figure 3In the drilling machine 400 shown, when drilling the electronic substrate, the control device 35 issues a pulse laser output command to the Q-switched laser oscillator 100 in such a manner that the pulse laser is irradiated to the processing object 405 after the positioning of the galvano-controlled mirror 403 is completed. Alternatively, in order to reduce the time loss caused by the delay of the command signal, the control device 35 predicts the positioning timing of the galvano-controlled mirror 403 and issues a pulse laser output command to the Q-switched laser oscillator 100 before the positioning of the galvano-controlled mirror 403 is completed in such a manner that the pulse laser is irradiated to the processing object 405 just after the positioning is completed. In either case, the generation timing of the pulse laser depends on the positioning timing of the galvano-controlled mirror 403. At this time, using the trained model obtained by the learning device 60, the inference device 80 can determine the transmittance of the optical switch element 26 based on the state quantity including the interval information indicating the time interval for generating the pulse laser and the target value of the amplified pulse energy. Therefore, by using the trained model, even when the generation interval of the pulse laser light is not determined in advance, the transmittance of the optical switch element 26 can be determined for each pulse laser light, and the amplified pulse energy can be controlled.

[0133] In the present embodiment, the case where the supervised learning is applied to the learning algorithm used by the model generation unit 62 is described, but the present invention is not limited thereto. As for the learning algorithm, in addition to supervised learning, reinforcement learning, unsupervised learning, semi-supervised learning, etc. can also be applied.

[0134] In addition, the model generation unit 62 may also learn the transmittance according to the learning data created for a plurality of laser devices 500. In addition, the model generation unit 62 may obtain the learning data from a plurality of laser devices 500 used in the same area, or may learn the transmittance using the learning data collected from a plurality of laser devices 500 operating independently in different areas. In addition, the laser device 500 for collecting the learning data may be added to the object midway, or removed from the object. Furthermore, the learning device 60 obtained by learning the transmittance for a certain laser device 500 may be applied to other laser devices 500, and the transmittance for the other laser devices 500 may be re-learned and updated.

[0135] In addition, as a learning algorithm used in the model generation unit 62, deep learning that learns the extraction of feature quantities themselves can also be used, and machine learning can also be performed according to other well-known methods such as genetic programming, functional logic programming, support vector machines, etc.

[0136] In addition, the learning device 60 and the inference device 80 are used to learn the transmittance of the optical switch element 26 of the laser device 500, but they can also be connected to the laser device 500 via a network, for example, and are separate devices from the laser device 500. In addition, the learning device 60 and the inference device 80 can also be built into the laser device 500 or the laser processing device 510. For example, at least one of the learning device 60 and the inference device 80 can be a part of the function of the control device 35 or the information processing device 36. In addition, the learning device 60 and the inference device 80 can also exist on a cloud server.

[0137] In the above description, the amplified pulse energy is stabilized by controlling the transmittance of the optical switch element 26 , but the amplified pulse energy may be stabilized by controlling the transmittance of the optical switch element 26 and the discharge drive current or the discharge power.

[0138] In addition, as shown in embodiment 1, when the positioning time of the electrically controlled mirror 403 is too short and the pulse energy output from the amplifier 200 is less than the desired value, the following control can be performed, that is, the electrically controlled mirror 403 is stopped after amplification until the required pulse energy is obtained, and the pulse laser is irradiated at the moment when the required pulse energy is obtained.

[0139] For example, in a CO2 laser, the oscillation efficiency varies according to the gas temperature and gas pressure. Therefore, in order to correct the changes in pulse energy caused by gas temperature and gas pressure and the transmittance of the optical switch element 26, these parameters can be used as state quantities for machine learning. In addition, sometimes if the discharge is performed continuously, the pulse energy decreases due to the degradation of the laser gas. Therefore, by using the continuous discharge time of the laser device 500 as the state quantity for machine learning, the transmittance of the optical switch element 26 and its dependence on the pulse energy can be calculated, which can be used to correct the transmittance or pulse energy of the optical switch element 26. In addition, the total discharge time from the time the optical component is replaced becomes an indicator of the degradation state of the optical component. If the optical component is degraded, the pulse energy sometimes changes due to the reduction of its reflectivity and transmittance. Therefore, the total discharge time from the time the optical component is replaced can be used as the state quantity for machine learning.

[0140] As described above, the laser device 500 according to the fourth embodiment can further include a learning device 60. The learning device 60 includes: a learning data acquisition unit 61 that acquires learning data, the learning data including a state quantity and a transmittance of the optical switch element 26, the state quantity including interval information indicating a time interval at which the laser device 500 generates a pulse laser and a pulse energy after the pulse laser is amplified; and a model generation unit 62 that generates a trained model using the learning data, the trained model being used to infer the transmittance of the optical switch element 26 at which the amplified pulse energy becomes a target value based on the state quantity.

[0141] In addition, the laser device 500 according to the fourth embodiment may further include an estimation device 80. The estimation device 80 includes an estimation data acquisition unit 81 that acquires a state quantity including interval information indicating a time interval for generating pulse laser light and a target value of pulse energy after amplification of the pulse laser light, and an estimation unit 82 that estimates the transmittance based on the state quantity acquired by the estimation data acquisition unit 81, using a trained model for estimating the transmittance of the optical switch element 26 at which the amplified pulse energy becomes the target value based on the state quantity. The control device 35 controls the optical switch element 26 using the transmittance estimated by the estimation device 80.

[0142] In addition, the interval information used by the learning device 60 and the inference device 80 respectively may be, for example, information including the pulse characteristic time of the pulse laser generated by the Q-switched laser oscillator 100, the energy of the pulse laser generated by the Q-switched laser oscillator 100, the waveform of the pulse laser generated by the Q-switched laser oscillator 100, the waveform of the pulse laser amplified by the amplifier 200, and at least one of the driving current or discharge power of the Q-switched laser oscillator 100 and the amplifier 200.

[0143] In addition, in the case where the laser device 500 is a gas laser, the state quantities used by the learning device 60 and the inference device 80 may be information including at least one of the cooling water temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas pressure of the Q-switched laser oscillator 100 or the amplifier 200, the continuous discharge time of the Q-switched laser oscillator 100 or the amplifier 200, the electrode temperature of the Q-switched laser oscillator 100 or the amplifier 200, and the total discharge time of the Q-switched laser oscillator 100 or the amplifier 200 from the time the optical components are replaced.

[0144] The learning device 60 and the estimation device 80 may be devices separate from the laser device 500. A laser processing system including at least one of the learning device 60 and the estimation device 80, which are devices separate from the laser device 500, may be configured.

[0145] Implementation method 5.

[0146] In the fourth embodiment, the transmittance of the optical switch element 26 is learned so that the amplified pulse energy reaches the target value. However, when the pulse laser output by the laser device 500 is used for hole drilling of an electronic substrate, it is more preferable that the processed shape is stable.

[0147] Therefore, in the fifth embodiment, a method of learning the transmittance so that the shape of the processed hole after processing becomes the target shape will be described.

[0148] Fig.15 is a diagram showing a configuration of a learning device 60a according to Embodiment 5. The learning device 60a performs, for example, Figure 3 The machine learning related to the laser processing device 510 shown in FIG. 6 is a machine learning device 60a. The learning device 60a includes a learning data acquisition unit 61a that acquires learning data used for learning, and a model generation unit 62a that uses the learning data to generate a trained model for estimating the transmittance of the optical switch element 26. The model generation unit 62a stores the generated trained model in the trained model storage unit 70a.

[0149] The learning data acquisition unit 61a acquires the state quantity including the interval information indicating the time interval at which the laser device 500 of the laser processing device 510 generates the pulsed laser and the shape information indicating the shape of the processed hole processed by the laser processing device 510, and the transmittance of the optical switch element 26 as the learning data. The interval information may be any information as long as it is information indicating the time interval at which the pulsed laser is generated. The interval information is, for example, information including the pulse characteristic time, the energy of the pulsed laser generated by the Q-switched laser oscillator 100, the waveform of the pulsed laser generated by the Q-switched laser oscillator 100, the waveform of the pulsed laser amplified by the amplifier 200, and at least one of the driving current or the discharge current of the Q-switched laser oscillator 100 and the amplifier 200. For example, the learning device 60a acquires the shape information indicating the shape of the processed hole processed when the time interval at which the pulsed laser is generated and the transmittance of the optical switch element 26 are changed to various values, and acquires the state quantity including the interval information and the shape information at this time and the set transmittance as the learning data.

[0150] In addition, when the laser medium of the laser device 500 is a gas laser serving as a gas, the state quantity obtained by the learning data acquisition unit 61a may also include at least one of the cooling water temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas pressure of the Q-switched laser oscillator 100 or the amplifier 200, the continuous discharge time of the Q-switched laser oscillator 100 or the amplifier 200, the electrode temperature of the Q-switched laser oscillator 100 or the amplifier 200, and the total discharge time of the Q-switched laser oscillator 100 or the amplifier 200 from the time the optical components are replaced.

[0151] The model generation unit 62a learns the transmittance of the optical switch element 26 based on the learning data created based on the combination of the state quantity including the spacing information output from the learning data acquisition unit 61a and the shape information indicating the shape of the processed hole processed by the laser processing device 510, and the transmittance of the optical switch element 26. Specifically, the model generation unit 62a generates a trained model for estimating the transmittance of the optical switch element 26 so that the shape of the processed hole after processing becomes a desired shape based on the state quantity of the laser processing device 510. Here, the learning data is data in which the state quantity and the transmittance of the optical switch element 26 are associated with each other.

[0152] The learning algorithm used by the model generation unit 62a can use a known algorithm such as tutored learning, untutored learning, reinforcement learning, etc. As an example, a case where a neural network is applied will be described.

[0153] The model generation unit 62a learns the transmittance of the optical switch element 26 by so-called tutor learning, for example, according to the neural network model. Here, tutor learning refers to a method in which a data set of input and result (label) is given to the learning device 60a, thereby learning the features in their learning data and inferring the result based on the input.

[0154] The neural network is composed of an input layer composed of multiple neurons, a hidden layer composed of multiple neurons, that is, an intermediate layer, and an output layer composed of multiple neurons. The intermediate layer can be 1 layer or more than 2 layers. Fig.11 The neural network shown.

[0155] In the fifth embodiment, the neural network learns the transmittance so that the shape of the processed hole becomes a desired shape through so-called supervised learning according to the learning data created based on the combination of the state quantity and transmittance acquired by the learning data acquisition unit 61a.

[0156] That is, the neural network learns by adjusting weights W1 and W2 so that the state quantity including the target value of the amplified pulse energy is input to the input layer and the result output from the output layer is close to the transmittance of the optical switch element 26 when the amplified pulse energy becomes the target value.

[0157] The model generation unit 62a generates a trained model by executing the above-described learning, and outputs the trained model to the trained model storage unit 70a.

[0158] The trained model storage unit 70 a stores the trained model output from the model generation unit 62 a .

[0159] The process flow of learning by the learning device 60a is the same as that of the learning device 60 according to the fourth embodiment, and therefore the description thereof is omitted here.

[0160] Fig.16 1 is a block diagram of an estimation device 80a related to the laser processing device 510. The estimation device 80a includes an estimation data acquisition unit 81a and an estimation unit 82a.

[0161] The inference data acquisition unit 81a acquires state quantities as inference data. The state quantities include the above-mentioned interval information and the target shape of the processed hole after processing. In addition, when the laser medium of the laser device 500 is a gas laser as a gas, the state quantities acquired by the inference data acquisition unit 81a may further include at least one of the cooling water temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas temperature of the Q-switched laser oscillator 100 or the amplifier 200, the gas pressure of the Q-switched laser oscillator 100 or the amplifier 200, the continuous discharge time of the Q-switched laser oscillator 100 or the amplifier 200, the electrode temperature of the Q-switched laser oscillator 100 or the amplifier 200, and the total discharge time of the Q-switched laser oscillator 100 or the amplifier 200 from the time of replacement of the optical component.

[0162] The inference unit 82a infers the transmittance obtained using the trained model. That is, the inference unit 82a can output the transmittance inferred from the state quantity so that the shape of the processed hole becomes the target shape by inputting the inference data acquired by the inference data acquisition unit 81a into the trained model stored in the trained model storage unit 70a.

[0163] In addition, the trained model used by the inference device 80a can be a trained model learned by using learning data obtained from the laser device 500 that is the inference object of the inference device 80a, and can be a trained model obtained from outside such as other laser devices 500 that are different from the laser device 500 that is the inference object of the inference device 80a and used.

[0164] The flow of the estimation operation of the estimation device 80a is the same as that of the estimation device 80 according to the fourth embodiment, and therefore the description thereof is omitted here.

[0165] For example, in Figure 3 In the drilling machine 400 shown, when drilling a hole on an electronic substrate, the control device 35 issues a pulse laser output command to the Q-switched laser oscillator 100 so that the pulse laser is irradiated to the object 405 after the positioning of the galvano-mirror 403 is completed. Alternatively, in order to reduce the time loss caused by the delay of the command signal, the control device 35 predicts the positioning timing of the galvano-mirror 403 and issues a pulse laser output command to the Q-switched laser oscillator 100 before the positioning of the galvano-mirror 403 is completed so that the pulse laser is irradiated to the object 405 just after the positioning is completed. In either case, the generation timing of the pulse laser depends on the positioning timing of the galvano-mirror 403. At this time, using the trained model obtained by the learning device 60a, the inference device 80a can determine the transmittance of the optical switch element 26 based on the state quantity including the interval information indicating the time interval for generating the pulse laser and the target shape of the processed hole. Therefore, by using the trained model, even when the generation interval of the pulse laser light is not determined in advance, the transmittance of the optical switch element 26 can be determined for each pulse laser light, and the amplified pulse energy can be controlled.

[0166] In addition, in the present embodiment, the case where the supervised learning is applied to the learning algorithm used by the model generation unit 62a is described, but the present invention is not limited to this. As for the learning algorithm, in addition to supervised learning, reinforcement learning, unsupervised learning, semi-supervised learning, etc. can also be applied.

[0167] In addition, the model generation unit 62a may also learn the transmittance according to the learning data created for a plurality of laser devices 500. In addition, the model generation unit 62a may obtain the learning data from a plurality of laser devices 500 used in the same area, or may learn the transmittance using the learning data collected from a plurality of laser devices 500 operating independently in different areas. In addition, the laser device 500 for collecting the learning data may be added to the object midway, or removed from the object. Furthermore, the learning device 60a obtained by learning the transmittance for a certain laser device 500 may be applied to other laser devices 500, and the transmittance for the other laser devices 500 may be re-learned and updated.

[0168] In addition, as a learning algorithm used in the model generation unit 62a, deep learning that learns the extraction of feature quantities themselves can also be used, and machine learning can also be performed according to other well-known methods such as genetic programming, functional logic programming, support vector machines, etc.

[0169] In addition, the learning device 60a and the inference device 80a are used to learn the transmittance of the optical switch element 26 of the laser device 500, but they may be connected to the laser device 500 via a network, for example, and may be separate devices from the laser device 500. In addition, the learning device 60a and the inference device 80a may be built into the laser device 500. Furthermore, the learning device 60a and the inference device 80a may exist on a cloud server.

[0170] In the above description, the amplified pulse energy is stabilized by controlling the transmittance of the optical switch element 26 , but the amplified pulse energy may be stabilized by controlling the transmittance of the optical switch element 26 and the discharge drive current or the discharge power.

[0171] In addition, as shown in embodiment 1, when the positioning time of the electrically controlled mirror 403 is too short and the pulse energy output from the amplifier 200 is less than the desired value, the following control can be performed, that is, the electrically controlled mirror 403 is stopped after amplification until the required pulse energy is obtained, and the pulse laser is irradiated at the moment when the required pulse energy is obtained.

[0172] For example, in a CO2 laser, the oscillation efficiency varies according to the gas temperature and gas pressure. Therefore, in order to correct the changes in pulse energy caused by gas temperature and gas pressure and the transmittance of the optical switch element 26, these parameters can be used as state quantities for machine learning. In addition, sometimes if the discharge is performed continuously, the pulse energy decreases due to the degradation of the laser gas. Therefore, by using the continuous discharge time of the laser device 500 as the state quantity for machine learning, the transmittance of the optical switch element 26 and its dependence on the pulse energy can be calculated, which can be used to correct the transmittance or pulse energy of the optical switch element 26. In addition, the total discharge time from the time the optical component is replaced becomes an indicator of the degradation state of the optical component. If the optical component is degraded, the pulse energy sometimes changes due to the reduction of its reflectivity and transmittance. Therefore, the total discharge time from the time the optical component is replaced can be used as the state quantity for machine learning.

[0173] As described above, the learning device 60a according to the fifth embodiment learns the transmittance of the optical switch element 26 of the laser device 500 of the laser processing device 510, and the learning device 60a includes: a learning data acquisition unit 61a that acquires learning data, the learning data including a state quantity and the transmittance of the optical switch element 26, the state quantity including interval information indicating the time interval for generating the pulsed laser and shape information indicating the shape of the processed hole processed by the pulsed laser; and a model generation unit 62a that uses the learning data to generate a trained model for estimating the transmittance of the optical switch element so that the shape of the processed hole becomes a target shape based on the state quantity. By having the above-mentioned structure, it is possible to learn the relationship between the transmittance and the state quantity so that the shape of the processed hole after processing is homogenized.

[0174] In addition, the estimation device 80a according to the fifth embodiment estimates the transmittance of the optical switch element 26 provided in the laser device 500 of the laser processing device 510, and the estimation device 80a includes: an estimation data acquisition unit 81a that acquires state quantities including interval information indicating the time interval for generating pulsed laser light and shape information indicating the target shape of a processing hole to be processed using the pulsed laser light; and an estimation unit 82a that estimates the transmittance based on the state quantities and the target shape acquired by the estimation data acquisition unit 81a using a trained model for estimating the transmittance of the optical switch element based on the state quantities and the shape information. By using the estimation device 80a as described above, it is possible to estimate the transmittance such that the shape of the processed hole after processing is homogenized.

[0175] The learning device 60a and the estimation device 80a may be built in the laser device 500 or the laser processing device 510, or may be separate devices from the laser device 500 and the laser processing device 510. In addition, a laser processing system including at least one of the learning device 60a and the estimation device 80a may be configured.

[0176] Implementation method 6.

[0177] In the first embodiment, the transmittance of the optical switch element 26 is determined for each pulse laser, and the transmittance when each pulse laser is generated is set to be constant.

[0178] However, when the Q-switched laser oscillator 100 generates pulse lasers having different pulse intervals, the pulse waveforms may not be similar. Fig.17 This is a diagram showing an example of the waveform of pulsed laser light having different pulse intervals.

[0179] Fig.17 (a) shows the waveform of the pulse laser oscillated by the Q-switched laser oscillator 100 . Fig.17 (b) shows the transmittance of the optical switch element 26 . Fig.17 (c) shows the waveform of the pulse laser input to the amplifier 200 . Fig.17 (d) shows the waveform of the pulse laser output from the amplifier 200 .

[0180] like Fig.17 As shown in (a), the waveform of the pulsed laser output by the Q-switched laser oscillator 100 is sometimes not similar when generating pulsed lasers with different pulse intervals, and the intensity ratio of the peak value of the pulse front part and the stable value of the pulse rear part is different. For example, the peak value p2 of the pulsed laser #2 and the peak value p3 of the pulsed laser #3 are greatly different, while the stable value c2 of the pulsed laser #2 and the stable value c3 of the pulsed laser #3 are approximately the same value. In the above case, by the same method as in the first embodiment, as Fig.17 As shown in (b), if the transmittance is controlled to be constant for each pulse laser, then Fig.17 As shown in (d), the pulse energy of the amplified pulse laser is equal, but the waveform is different. Here, Fig.17 (c) is the waveform of the laser pulse light input to the amplifier 200 .

[0181] As described above, when the waveforms of the plurality of pulse lasers generated by the Q-switched laser oscillator 100 are not similar, Fig.18 As shown, by changing the transmittance of the optical switch element 26 within one pulse time, not only the pulse energy but also the waveform can be homogenized.

[0182] Fig.18 This is an explanatory diagram of an example in which the transmittance is changed over time within the pulse time. Fig.18 (a) shows the waveform of the pulse laser oscillated by the Q-switched laser oscillator 100 . Fig.18 (b) shows the transmittance of the optical switch element 26 . Fig.18 (c) shows the waveform of the pulse laser input to the amplifier 200 . Fig.18 (d) shows the waveform of the pulse laser output from the amplifier 200 .

[0183] Furthermore, when the transmittance is set as described above using machine learning, the state quantity may further include at least one of the pulse energy of the pulse laser, the pulse peak value of the pulse front portion, and the pulse stable value of the pulse rear portion, and at least one of the timing of generating the pulse laser by the Q-switched laser oscillator 100. In addition, the transmittance as a learning result is not a constant value for each pulse laser, but may be a value that changes over time while one pulse laser is transmitted.

[0184] As described above, the laser device 500 according to the sixth embodiment changes the transmittance over time during the period when one pulse laser passes through the optical switch element 26. Thus, the waveform of the amplified laser pulse light can be homogenized. In addition, when the transmittance is set using machine learning, the model generation unit 62, 62a of the learning device 60, 60a can also generate a trained model for inferring the transmittance that changes over time during the period when one pulse laser passes through the optical switch element 26 based on the state quantity.

[0185] Implementation method 7.

[0186] When the interval of pulse laser generation is shortened, not only the interval of pulse lasers until the last one, but also the history of multiple laser pulses will have an impact. In this case, the interval information included in the state quantity shown in Embodiments 4 to 6 is not only the time interval between the target pulse laser and the last pulse laser, but also can be set as information indicating multiple time intervals related to multiple pulse lasers included in a certain time.

[0187] Fig.19 This is an explanatory diagram related to the control of transmittance involved in the seventh embodiment. Fig.19 (a) shows the waveform of the pulse laser oscillated by the Q-switched laser oscillator 100 . Fig.19 (b) shows the transmittance of the optical switch element 26 . Fig.19 (c) shows the waveform of the pulse laser input to the amplifier 200 . Fig.19 (d) shows the waveform of the pulse laser output from the amplifier 200 .

[0188] like Fig.19As shown in (a), for the case where pulse lasers #1 to #6 oscillate at a constant time interval, when the time interval is short, each pulse laser #1 to #6 is not only affected by the previous pulse laser, but sometimes also by multiple pulse lasers. In this case, when the pulse lasers #1 to #6 oscillate at a constant interval, and the length of the affected period is set to TL, in pulse laser #1, one pulse laser is included in the period of TL before the generation time of pulse laser #1, while in pulse laser #3, two pulse lasers #1 to #2 are included in the period of TL before the generation time of pulse laser #3. In addition, in pulse laser #4, three pulse lasers #1 to #3 are included in the period of TL before the generation time of pulse laser #4. As for pulse lasers #5 and #6, similarly to pulse laser #4, three pulse lasers are included in the period of TL before the generation time of each pulse laser. Therefore, the pulse energy varies in pulse lasers #1 to #4, and the pulse energy is constant in pulse lasers #4 to #6. In this case, if the moving average value of the total value of the time interval between the pulse lasers during the period of TL affected by the pulse laser is as follows: Fig.19 The transmittance is controlled as shown in (b), then Fig.19 As shown in (d), the fluctuation of the amplified pulse energy can be suppressed.

[0189] In addition, the value of TL varies depending on conditions such as pulse output. Therefore, as shown in embodiments 4 and 5, when machine learning is used, the value of TL is also changed and data is obtained through various conditions. The value of TL is included in the state quantity and machine learning is performed to obtain the optimal range.

[0190] Implementation method 8.

[0191] When the interval between pulse laser generation is sufficiently long, the discharge power may be varied. For example, when the laser device 500 is a three-axis orthogonal CO2 laser, it takes a certain amount of time from the start of discharge until the gain rises.

[0192] Fig. 20 1 is a diagram showing a partial structure between electrodes 11 of a laser device 500 according to Embodiment 8. Fig. 20 Only a portion of the electrode 11 is shown, and the electrode 12 is not shown.

[0193] Fig. 20 Observed from the optical axis Figure 2 FIG. 5 is a diagram of a discharge space between electrodes 11 of a laser device 500 shown in FIG. Fig. 20 In this figure, Vg is the gas flow rate, and Dwd is the electrode width of the electrode 11 in the gas flow direction 13.

[0194] Fig.21 Yes means Fig. 20 Graph of the gain distribution in a steady state between the electrodes 11 of the laser device 500 of the structure shown. The time corresponding to the flow of the laser gas from the end to the end of the electrode 11 in the width direction of the electrode 11, i.e., the gas flow direction 13, from the start of the discharge to the gain distribution in a steady state. That is, if the time from the start of the discharge to the gain distribution becoming a steady state is set to τ, then τ = Dwd / Vg. For example, in the case of gas flow rate Vg = 80m / s and electrode width Dwd = 40mm, it becomes τ = 0.5msec. That is, in the case where the time interval for generating pulsed laser is longer than the above τ, in order to suppress power consumption and stop the discharge, the discharge can be started before τ when the next pulsed laser is generated. In addition, in the case where the time interval for generating pulsed laser is shorter than the above τ, control can be performed to reduce the discharge power when the pulse energy is too large. If the above control is performed, the energy efficiency can be improved even when the pulse frequency is low. In addition, since it is not affected by the previous pulsed laser during the time longer than τ, the value of TL described in Embodiment 7 can be set to τ.

[0195] As described above, in the laser device 500 according to the eighth embodiment, the pulse characteristic time is equal to or less than the value obtained by dividing the length of the discharge electrodes, i.e., the electrodes 11 and 12, in the direction of the laser gas flow, i.e., the electrode width Dwd of the discharge electrodes, of the Q-switched laser oscillator 100 by the gas flow rate Vg. Thus, the pulse energy of the pulse laser output from the amplifier 200 can be stabilized, and the processed shape of the processing performed using the laser device 500 can be made uniform.

[0196] Implementation method 9.

[0197] Fig. 22 1 is a diagram showing the internal structure of a laser device 500a according to Embodiment 9. In the laser device 500a, a part of the structure of the part constituting the resonator is different from that of the laser device 500. Specifically, in the laser device 500a, a total reflection mirror 54 is provided instead of the total reflection mirror 21. The total reflection mirror 54 is obtained by combining two plane mirrors whose normal lines are orthogonal to each other. At this time, the two normal lines are parallel to the electrode surface, that is, parallel to the XZ plane. Therefore, the total reflection mirror 54 becomes a recursive reflection mirror in the XZ plane direction.

[0198] If viewed from the optical axis Fig. 22 The discharge space between the electrodes 11 of the laser device 500a shown in FIG. Fig. 20 The same state as shown. In addition, Fig.23 1 is a diagram showing a temperature distribution between the electrodes 11 of the laser device 500 a in a steady state.

[0199] While the laser gas flows from the upstream side of the gas flow, i.e., the positive direction of the X-axis, toward the downstream side, i.e., the negative direction of the X-axis, power is input by continuous discharge. Therefore, a temperature distribution is generated in the gas flow direction 13, and the temperature of the laser gas on the downstream side becomes higher than that on the upstream side. Therefore, a refractive index distribution is generated in the laser gas between the electrodes 11, and the optical axis of the light transmitted in this part is slightly bent. In a resonator using a conventional concave mirror pair, in this case, the optical axis moves to the upstream side of the gas flow, and the oscillation stops depending on the situation. In embodiment 9, the resonator is constructed using a total reflection mirror 54 as a recursive reflection mirror, so that the position of the optical axis of the resonance condition is limited to the tangent of the two mirrors of the recursive reflection mirror. That is, when a recursive reflection mirror is used, even if a temperature distribution is generated in the gas flow direction, the movement of the optical axis is limited, and stable oscillation can be achieved. In this case, with respect to the pulse energy and pulse waveform of the oscillator, the mirror after the output from the resonator can be set to a partial reflection mirror 55 instead of the mirror 25 in the laser device 500, and a part of the transmitted light can be observed by the optical sensor 50. Fig. 22 In the figure, the partial reflection mirror 24 and the total reflection mirror 54 as a recursive reflection mirror are arranged on a straight line, but a return mirror may be arranged between the partial reflection mirror 24 and the total reflection mirror 54.

[0200] As described above, the Q-switched laser oscillator 100 of the laser device 500a according to Embodiment 9 includes a recursive mirror as the total reflection mirror 54 constituting the resonator. Thus, even when temperature distribution occurs in the gas flow direction, stable oscillation can be achieved.

[0201] Implementation method 10.

[0202] exist Figure 2 In the laser device 500 shown, the Q-switched laser oscillator 100 and the amplifier 200 are housed in the same housing 300 and share the laser medium. Therefore, the state of the gain of the amplifier 200 can be estimated based on the pulse energy of the Q-switched laser oscillator 100. For example, it is known that when the laser gas deteriorates and the pulse energy of the pulsed laser in the oscillation stage decreases, the gain of the amplifier stage also decreases. The relationship between the state of the gain in the amplifier 200 and the pulse energy in the Q-switched laser oscillator 100 is modeled, and the transmittance of the optical switch element 26 is corrected based on the model, thereby stabilizing the pulse energy after amplification, and as a result, the processing shape of the laser processing using the pulsed laser can be homogenized.

[0203] Fig.24 is a flowchart for explaining the operation of the laser processing device 510 according to the tenth embodiment. Figure 8 etc., so the description is omitted here.

[0204] The control device 35 stores the calculated transmittance data of the optical switch element 26 in, for example, a memory within the control device 35 , and sets the transmittance of the optical switch element 26 for each pulse laser (step S131 ).

[0205] The control device 35 uses the oscillation interval of the pulsed laser calculated in step S103 and the transmittance of the optical switch element 26 set in step S131 to control the Q-switched laser oscillator 100 and the optical switch element 26, so that the Q-switched laser oscillator 100 oscillates the laser with one pulse (step S132).

[0206] Furthermore, the control device 35 obtains the pulse energy of the pulse laser light of the Q-switched laser oscillator 100 obtained by the optical sensor 50 via the information processing device 36 (step S133 ).

[0207] When the laser processing device 510 performs hole drilling of the electronic substrate by one hole using the pulsed laser oscillated by the laser device 500 (step S134), the process returns to step S132. In addition, in parallel with the implementation of the hole drilling process, the control device 35 calculates the pulse energy of the next pulsed laser based on the model (step S135). The model used here is a model that represents the relationship between the state of the gain in the above-mentioned amplifier 200 and the pulse energy in the Q-switched laser oscillator 100. The control device 35 corrects the transmittance of the optical switch element 26 based on the pulse energy of the next pulsed laser calculated according to the model (step S136), and returns to the process of step S131.

[0208] By performing the above-described processing, the pulse energy of the oscillation stage is acquired every time one pulse oscillates, and the transmittance of the optical switch element can be corrected based on the model until the next pulse laser oscillates.

[0209] At this point, model creation can be done through machine learning.

[0210] 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.

[0211] For example, in the above-mentioned embodiments 1 to 10, the laser devices 500 and 500a are set to be gas lasers whose laser medium is gas, but the variation of the pulse energy during oscillation of the Q-switched laser oscillator 100 when the oscillation interval of the pulsed laser is changed has the same influence on solid-state lasers, etc. Therefore, if the peculiar parts of the gas laser shown above are removed, the above-mentioned structure can also be applied to solid-state lasers, etc., and the same effect can be expected.

[0212] In the above description, the example of controlling the transmittance of the optical switch element 26 is mainly described. Figure 2 As shown, when the laser device 500 includes a plurality of optical switch elements 26 and 27 , control may be performed so that the transmittance of the plurality of optical switch elements 26 and 27 combined satisfies the above-mentioned condition.

[0213] Description of the label

[0214] 1, 2, 3 optical axis, 11, 12 electrodes, 13, 14, 15, 16 air flow direction, 21, 54 total reflection mirror, 22 Q switch, 23, 29, 33 window, 24, 34, 55 partial reflection mirror, 25, 28, 30, 31, 32, 401, 402 mirror, 26, 27 optical switch element, 35 control device, 36 information processing device, 40, 41 blower, 42, 43 heat exchanger, 44 discharge control device, 50, 51 optical sensor, 60, 6 0a learning device, 61, 61a learning data acquisition unit, 62, 62a model generation unit, 70, 70a trained model storage unit, 80, 80a inference device, 81, 81a inference data acquisition unit, 82, 82a inference unit, 100Q switching laser oscillator, 200 amplifier, 300 frame, 400 hole processing machine, 403 electrically controlled reflector, 404 lens, 405 processing object, 500, 500a laser device, 510 laser processing device.

Claims

1. A laser device, characterized in that: have: A Q-switched laser oscillator, which enables pulsed laser generation; An amplifier, which amplifies the pulsed laser; an optical switch element disposed on an optical path between the Q-switched laser oscillator and the amplifier; as well as A control device modulates the transmittance of the optical switch element based on a pulse characteristic time representing a characteristic of a time interval at which the Q-switched laser oscillator generates the pulse laser light.

2. The laser device according to claim 1, characterized in that The control device, The time interval between the plurality of pulse lasers generated by the Q-switched laser oscillator or the moving average of the time interval between the plurality of pulse lasers generated by the Q-switched laser oscillator is obtained as the pulse characteristic time. The transmittance is increased as the time interval is shorter, and the transmittance is controlled so that the variation in energy between the plurality of pulse laser beams emitted from the amplifier becomes smaller than a predetermined value.

3. The laser device according to claim 1 or 2, characterized in that: It also has a learning device. The learning device comprises: a learning data acquisition unit that acquires learning data, the learning data including a state quantity and a transmittance of the optical switch element, the state quantity including interval information indicating a time interval at which the laser device generates the pulse laser and a pulse energy of the pulse laser after amplification; as well as A model generation unit generates a trained model for estimating the transmittance of the optical switch element at which the amplified pulse energy reaches a target value based on the state quantity, using the learning data.

4. The laser device according to any one of claims 1 to 3, characterized in that: It also has an estimation device for estimating the transmittance of the optical switch element, The inference device comprises: an estimation data acquisition unit that acquires a state quantity including interval information indicating a time interval for generating the pulse laser and a target value of a pulse energy after amplification of the pulse laser; and an estimating unit that estimates the transmittance of the optical switch element based on the state quantity acquired by the estimation data acquiring unit, using a trained model for estimating the transmittance of the optical switch element at which the amplified pulse energy becomes a target value based on the state quantity, and The control device controls the optical switch element using the transmittance estimated by the estimation device.

5. The laser device according to claim 3 or 4, characterized in that: The interval information includes the pulse characteristic time of the pulse laser generated by the Q-switched laser oscillator, the energy of the pulse laser generated by the Q-switched laser oscillator, the waveform of the pulse laser generated by the Q-switched laser oscillator, the waveform of the pulse laser after amplification by the amplifier, and at least one of the driving current or discharge power of the Q-switched laser oscillator and the amplifier.

6. The laser device according to any one of claims 3 to 5, characterized in that: The laser medium of the laser device is a gas laser as a gas, The state quantity also includes at least one of the cooling water temperature of the Q-switched laser oscillator or the amplifier, the gas temperature of the Q-switched laser oscillator or the amplifier, the gas pressure of the Q-switched laser oscillator or the amplifier, the continuous discharge time of the Q-switched laser oscillator or the amplifier, the electrode temperature of the Q-switched laser oscillator or the amplifier, and the total discharge time of the Q-switched laser oscillator or the amplifier from the time the optical components are replaced.

7. The laser device according to any one of claims 1 to 6, characterized in that: The pulse characteristic time is equal to or less than a value obtained by dividing the length of the discharge electrode in the gas flow direction of the Q-switched laser oscillator, that is, the electrode width, by the gas flow rate.

8. The laser device according to any one of claims 1 to 7, characterized in that: The control device changes the transmittance over time during a period in which one pulse laser light passes through the optical switch element.

9. The laser device according to claim 3, characterized in that: The model generation unit generates a trained model for estimating the transmittance that changes with time while one pulse of laser light passes through the optical switch element based on the state quantity.

10. A laser processing device, characterized in that: have: The laser device as claimed in claim 1; a deflection element that deflects the pulsed laser output from the amplifier; and an objective optical system that focuses or transfers the pulsed laser light from the deflection element and irradiates the object to be processed, The control device controls the transmittance in accordance with a processing hole characteristic value representing the characteristics of the processing holes included in a processing path when the processing object is opened by the pulse laser. The shorter the interval between the processing holes, the higher the transmittance is, and the transmittance is controlled so that the value representing the fluctuation of the shapes of the multiple processing holes is smaller than a predetermined value.

11. The laser processing device according to claim 10, characterized in that: The machined hole characteristic value is a value indicating the interval between the plurality of machined holes on the machining path, or a moving average of the intervals between the plurality of machined holes.

12. The laser processing device according to claim 10 or 11, characterized in that: The Q-switched laser oscillator includes a recursive mirror as a total reflection mirror constituting a resonator.

13. A learning device for learning the transmittance of the optical switch element of the laser device according to claim 1 or 2, The learning device is characterized by having: a learning data acquisition unit that acquires learning data, the learning data including a state quantity and a transmittance of the optical switch element, the state quantity including interval information indicating a time interval for generating the pulse laser and a pulse energy of the amplified pulse laser; and A model generation unit generates a trained model for estimating the transmittance of the optical switch element at which the pulse energy reaches a target value based on the state quantity, using the learning data.

14. A learning device for learning the transmittance of the optical switch element of the laser device of the laser processing device according to any one of claims 10 to 12, The learning device is characterized by having: a learning data acquisition unit that acquires learning data including a state quantity and a transmittance of the optical switch element, the state quantity including interval information indicating a time interval for generating the pulse laser and shape information indicating a shape of a processed hole processed using the pulse laser; and A model generating unit generates a trained model for estimating the transmittance of the optical switch element in which the shape of the processed hole becomes a target shape based on the state quantity, using the learning data.

15. The learning device according to claim 13 or 14, characterized in that: The interval information includes the pulse characteristic time of the pulse laser generated by the Q-switched laser oscillator, the energy of the pulse laser generated by the Q-switched laser oscillator, the waveform of the pulse laser generated by the Q-switched laser oscillator, the waveform of the pulse laser after amplification by the amplifier, and at least one of the driving current or discharge power of the Q-switched laser oscillator and the amplifier.

16. The learning device according to any one of claims 13 to 15, characterized in that: The laser medium of the laser device is a gas laser as a gas, The state quantity also includes at least one of the cooling water temperature of the Q-switched laser oscillator or the amplifier, the gas temperature of the Q-switched laser oscillator or the amplifier, the gas pressure of the Q-switched laser oscillator or the amplifier, the continuous discharge time of the Q-switched laser oscillator or the amplifier, the electrode temperature of the Q-switched laser oscillator or the amplifier, and the total discharge time of the Q-switched laser oscillator or the amplifier from the time the optical components are replaced.

17. An estimation device for estimating the transmittance of the optical switch element of the laser device according to claim 1 or 2, The inference device is characterized by having: an estimation data acquisition unit that acquires a state quantity including interval information indicating a time interval for generating the pulse laser and a target value of pulse energy after the pulse laser is amplified; and An estimating unit estimates the transmittance based on the state quantity and the target value acquired by the estimation data acquiring unit, using a trained model for estimating the transmittance of the optical switch element based on the state quantity and the target value.

18. An estimation device for estimating the transmittance of the optical switch element of the laser device of the laser processing device according to any one of claims 10 to 12, The inference device is characterized by having: an estimation data acquisition unit that acquires a state quantity including interval information indicating a time interval for generating the pulse laser and shape information indicating a target shape of a machined hole to be machined using the pulse laser; and An estimating unit estimates the transmittance based on the state quantity and the target shape acquired by the estimation data acquiring unit, using a trained model for estimating the transmittance of the optical switch element based on the state quantity and the shape information.

19. A laser processing system, characterized in that: have: A Q-switched laser oscillator, which enables pulsed laser generation; An amplifier, which amplifies the pulsed laser; an optical switch element disposed on an optical path between the Q-switched laser oscillator and the amplifier; a deflection element that deflects the pulsed laser output from the amplifier; an objective optical system that focuses or transfers the pulse laser light from the deflection element and irradiates the pulse laser light onto a processing object; and A control device controls the transmittance of the optical switch element in accordance with a processing hole characteristic value representing the characteristics of the processing holes included in a processing path when the processing object is opened by the pulse laser, wherein the transmittance is increased as the interval between the processing holes is shorter, and the transmittance is controlled so that the value representing the fluctuation of the shapes of the plurality of processing holes is less than a predetermined value.

20. The laser processing system according to claim 19, characterized in that: Also provided is a learning device, the learning device having: a learning data acquisition unit that acquires learning data including a state quantity and shape information indicating a shape of a processed hole processed using the pulse laser, the state quantity including interval information indicating a time interval for generating the pulse laser; as well as A model generating unit generates a trained model for estimating the transmittance of the optical switch element in which the shape of the processed hole becomes a target shape based on the state quantity, using the learning data.

21. The laser processing system according to claim 19 or 20, characterized in that: Also provided is an inference device, the inference device having: an estimation data acquisition unit that acquires a state quantity and shape information indicating a target shape of a machined hole to be machined using the pulse laser, the state quantity including interval information indicating a time interval for generating the pulse laser; as well as An estimating unit estimates the transmittance based on the state quantity and the target shape acquired by the estimation data acquiring unit, using a trained model for estimating the transmittance of the optical switch element based on the state quantity and the shape information.

22. A laser processing method, characterized in that: The following steps are included: enabling pulse laser to be generated; Setting the transmittance of the optical switch element that transmits the pulse laser light; The pulse energy of the pulse laser light is changed by injecting the pulse laser light into the optical switch element having a set transmittance; amplifying the pulsed laser; deflecting the amplified pulse laser to adjust the position where the pulse laser irradiates the object to be processed; as well as The deflected pulse laser is focused or transferred to irradiate the processing object, In the step of changing the pulse energy of the pulse laser, the transmittance of the optical switch element is modulated based on a pulse characteristic time that indicates a characteristic of a time interval for generating the pulse laser.

Images