Processing system and processability determination system

Abstract

To reduce processing failures by accurately determining processability based on a processing condition of a processed material before processing without being affected by a surface state.SOLUTION: A processing system includes a laser processing device capable of executing a processing step for irradiating a laser beam to a processed material under a processing irradiation condition to perform processing and a processability determination step for irradiating the laser beam to the processed material under a determination irradiation condition different from the processing irradiation condition, an imaging device capable of imaging the processed material, a surface determination device for determining a surface state of the processed material on the basis of image information obtained by imaging the processed material by the imaging device and determining an irradiation position of the laser beam in the processability determination step on the basis of the determination result of the surface state of the processed material, and a processability determination device for determining the processability of the processed material on the basis of light generated by irradiating the laser beam to the irradiation position of the processed material under the determination irradiation condition by the laser processing device in the processability determination step.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a machining system and a machining performance determination system. [Background technology]

[0002] Conventionally, in laser processing devices such as laser processing machines, processing conditions are generally set in advance according to the material and thickness of the workpiece. Therefore, an operator (user) of the laser processing device selects processing conditions that match the material and thickness of the workpiece, or performs laser processing under processing conditions instructed by a processing program.

[0003] However, even for workpieces of the same material and thickness, good processing quality may not be obtained under the processing conditions previously prepared in the laser processing device due to individual differences in the country of manufacture, manufacturer, production lot, storage conditions, etc. On the other hand, there is also known a technique in which processing conditions suitable for the material and thickness of the workpiece are selected, the actual material and thickness of the workpiece are measured, and the selected processing conditions are corrected according to the measurement results that also take into account measurement data on the surface condition of the workpiece (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6754614 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the device disclosed in Patent Document 1, the processing conditions selected according to the material and thickness of the workpiece can be corrected based on the actually measured material, thickness, and surface condition, but it is not intended to determine what level of processing quality can be obtained if the selected processing conditions are not corrected.

[0006] In other words, the above-mentioned conventional technology does not judge the workability (degree of suitability for cutting) of the workpiece based on the selected processing conditions before actual processing, taking into account the individual differences (quality variations) of the actual workpiece, which differ, for example, between manufacturers, between production lots, or between storage conditions.

[0007] Furthermore, the surface condition of the workpiece may be uneven due to localized rust and scratches, and even high-quality materials with no variations in material quality or thickness may be judged to have a poor surface depending on the location of the surface condition measurement. In this case, the measurement data for the surface condition may not accurately reflect the quality of the workpiece, which may affect the adjustment of processing conditions.

[0008] This poses a problem in that the operator (user) cannot accurately determine the workability based on the processing conditions of the workpiece before processing, without being affected by the surface condition, and based on the determination results, decide whether to process under the pre-set processing conditions or change to processing conditions suitable for the workpiece, without performing test processing (trial processing).

[0009] One aspect of the present invention is a processing system and a processability determination system that can accurately determine the processability based on the processing conditions of a workpiece before processing, without being affected by the surface condition, thereby reducing processing defects. [Means for solving the problem]

[0010] A processing system according to one aspect of the present invention includes a laser processing device capable of performing a processing step in which a workpiece is processed by irradiating it with laser light under processing irradiation conditions, and a processability judgment step in which the workpiece is irradiated with the laser light under judgment irradiation conditions that are different from the processing irradiation conditions; an imaging device capable of imaging the workpiece; a surface judgment device that judges the surface condition of the workpiece based on image information obtained by imaging the workpiece with the imaging device, and determines the irradiation position of the laser light in the processability judgment step based on the judgment result of the surface condition of the workpiece; and a processability judgment device that judges the processability of the workpiece based on light generated by the laser processing device irradiating the irradiation position of the workpiece with the laser light under the judgment irradiation conditions in the processability judgment step.

[0011] A workability determination system according to one embodiment of the present invention comprises a surface determination device that determines the surface condition of a workpiece based on image information obtained by imaging the workpiece with an imaging device capable of imaging the workpiece, and determines the irradiation position of laser light based on the determination result of the surface condition of the workpiece, and a workability determination device that determines the workability of the workpiece based on light generated by irradiating the laser light to the irradiation position of the workpiece under determination irradiation conditions that are different from the processing irradiation conditions.

[0012] According to a processing system and a machinability determination system according to one aspect of the present invention, the surface condition of a workpiece is determined based on image information obtained by capturing an image of the workpiece using an imaging device. Furthermore, the laser beam irradiation position in the machinability determination step is determined based on the determination result of the surface condition of the workpiece. Then, in the machinability determination step, the machinability of the workpiece is determined based on light generated by the laser processing device irradiating the workpiece with laser beam under the determination irradiation conditions at the irradiation position. This allows the machinability of the workpiece based on the processing conditions of the workpiece to be accurately determined before processing without being affected by the surface condition, making it easier to determine whether to perform actual processing using preset processing conditions or to change to processing conditions suitable for the workpiece, thereby reducing processing defects. [Effects of the Invention]

[0013] According to one aspect of the present invention, it is possible to accurately determine the workability based on the processing conditions of a workpiece before processing without being affected by the surface state, thereby reducing processing defects. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is an explanatory diagram schematically showing the basic configuration of a machining system according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing an example of time-series data based on the measurement results obtained by measuring, with a spectroscope, the emission spectrum generated when a workpiece is irradiated with laser light under the judgment irradiation conditions. [Figure 3] FIG. 3 is a diagram showing an example of a processing quality evaluation result that allows comparison between time waveforms of time-series data of reaction times, which show different surface states for each material of the processed material, and surface images including processing marks. [Figure 4] FIG. 4 is an explanatory diagram showing time waveforms of time-series data of reaction times of portions of the workpiece with different surface conditions and surface images. [Figure 5] FIG. 5 is a diagram illustrating surface images showing various surface states of the workpiece. [Figure 6] FIG. 6 is a schematic functional block diagram of the machining system. [Figure 7] FIG. 7 is a block diagram showing a schematic configuration of a surface determination unit used in the processing system. [Figure 8] FIG. 8 is an explanatory diagram that schematically shows the basic hardware configuration of a machinability determination system used in the machining system. [Figure 9] FIG. 9 is a flowchart showing an example of a processing flow of the machining system. [Figure 10] FIG. 10 is an explanatory diagram showing an example of various surface images showing the surface condition of the workpiece W. [Figure 11] FIG. 11 is a diagram showing a confusion matrix for explaining the result of the surface determination based on the surface determination model. [Figure 12] FIG. 12 is a diagram schematically illustrating an example of the configuration of a camera of the processing system according to the second embodiment. [Figure 13] FIG. 13 is an explanatory diagram schematically showing an example of camera installation in a processing system. [Figure 14] FIG. 14 is an explanatory diagram schematically showing an example of installation of cameras in a processing system. [Figure 15] FIG. 15 is a flowchart showing an example of a processing flow of the machining system. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, a machining system and a machinability determination system according to embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the following embodiments do not limit the invention according to each claim, and not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0016] In the following embodiments, the same or corresponding components are denoted by the same reference numerals, and redundant explanations are omitted. In the embodiments, the arrangement, scale, dimensions, etc. of each component may be exaggerated or minimized, and may not correspond to the actual ones, and some components may be omitted.

[0017] [First embodiment] [Basic configuration of the processing system] FIG. 1 is an explanatory diagram schematically showing the basic configuration of a machining system according to a first embodiment of the present invention.

[0018] As shown in FIG. 1, a processing system 100 according to a first embodiment includes a laser processing apparatus 10 that can perform a processing step in which a workpiece W is irradiated with a laser beam LB under processing irradiation conditions to perform processing (e.g., cutting) and a machinability evaluation step in which the workpiece W is irradiated with the laser beam LB under evaluation irradiation conditions that are different from the processing irradiation conditions. The processing system 100 also includes a camera (image capture device) 40 that can capture an image of the workpiece W. The processing system 100 also includes a personal computer (PC) 50 that determines the surface condition of the workpiece W based on image information obtained by capturing an image of the workpiece W with the camera 40 and determines the irradiation position of the laser beam LB in the machinability evaluation step based on the evaluation result of the surface condition of the workpiece W. In the machinability evaluation step, the PC 50 determines the machinability of the workpiece W based on light generated by the laser processing apparatus 10 irradiating the irradiation position of the workpiece W with the laser beam LB under evaluation irradiation conditions. Therefore, the PC 50 functions as a surface evaluation device and a machinability evaluation device. The machining system 100 includes, for example, an NC (Numerical Control) device 60. The PC 50 has a surface determination model 5 (FIG. 7), and inputs image information captured by the camera 40 to the surface determination model 5 as data for determining the surface condition, obtains a surface quality evaluation of the workpiece W, and determines the surface condition. The surface determination model 5 is created by machine learning, for example, by inputting the image information and a surface quality evaluation result 2 (FIG. 7) indicating the surface condition of the workpiece W as training data.

[0019] The processing system 100 also includes a spectrometer 30 that measures the emission spectrum generated when the workpiece W is irradiated with the laser beam LB under the judgment irradiation conditions, a radiation thermometer 30A that measures the infrared intensity of the radiation light generated when the workpiece W is irradiated with the laser beam LB under the judgment irradiation conditions, and a display 70 that can display various information. The PC 50 may be included in the NC device 60, and the NC device 60 may be mounted so as to be included in the laser processing device 10.

[0020] The workpiece W contains, for example, iron (Fe) as a main component if it is steel, and aluminum (Al) as a main component if it is a non-ferrous aluminum alloy steel. In addition to these main components, the workpiece W also contains elements intentionally added by the manufacturer and elements mixed in as impurities.

[0021] Steel is considered to contain at least carbon (C), manganese (Mn), silicon (Si), chromium (Cr), aluminum (Al), and titanium (Ti), which are elements that are more easily oxidized than iron (Fe). The term "impurities" used here refers to inclusions that are not the main components of the material, and includes substances that induce physical phenomena such as bubbles when the workpiece W is melted.

[0022] The laser processing apparatus 10 performs various processes such as marking, laser cutting, and laser drilling of the workpiece W (hereinafter, "cutting" and "drilling" are collectively referred to as "cutting processes"). The following description will mainly focus on cutting processes, but is not limited to this. The laser processing apparatus 10 has a processing stage 11 on which the workpiece W, such as sheet metal, is placed, and an X-axis carriage 12 that moves relative to the processing stage 11 in the X-axis direction of the processing stage 11 as indicated by the arrow in the figure. The laser processing apparatus 10 also has a Y-axis carriage 13 that moves on the X-axis carriage 12 in the Y-axis direction as indicated by the arrow in the figure, and a laser processing unit 20 that irradiates the workpiece W with laser light LB to perform processing.

[0023] The laser processing unit 20 includes a laser oscillator 21 that generates and emits laser light LB, and a laser processing head 22 that is mounted on, for example, a Y-axis carriage 13 and configured to be movable in the X-axis and Y-axis directions by the X-axis carriage 12 and the Y-axis carriage 13. The laser processing unit 20 also includes a process fiber 23 that transmits the laser light LB generated by the laser oscillator 21 to the laser processing head 22, and a camera 40 that is mounted on, for example, a side of the housing of the laser processing head 22.

[0024] Furthermore, the laser processing apparatus 10 is equipped with an assist gas supply device (not shown) that supplies assist gas. Note that the laser processing apparatus 10 is not limited to a configuration in which the laser processing head 22 moves relative to the workpiece W, and a configuration in which the workpiece W moves relative to the laser processing head 22 may also be employed. In this way, it is sufficient that the workpiece W and the laser processing head 22 are configured to be movable relative to each other.

[0025] The laser oscillator 21 may be, for example, a type in which seed light emitted from a laser diode is excited and amplified by Yb (ytterbium) or the like in a resonator, and laser light LB of a predetermined wavelength is emitted, or a type in which laser light LB emitted from a laser diode is directly utilized.

[0026] The laser oscillator 21 emits laser light LB in the 1 μm band with a wavelength of 900 nm to 1100 nm. For example, a DDL (Direct Diode Laser) oscillator emits laser light LB with a wavelength of 910 nm to 950 nm, and a fiber laser oscillator emits laser light LB with a wavelength of 1060 nm to 1080 nm.

[0027] The blue semiconductor laser emits laser light LB with a wavelength of 400 nm to 460 nm. The green laser may be a fiber laser oscillator or a DDL oscillator that emits laser light LB with a wavelength of 500 nm to 540 nm, or may be a multi-wavelength resonator that combines it with laser light LB in the 1 μm band. In addition, although not shown, a guide light GB (e.g., wavelength 650 nm) may be emitted to confirm the position on the workpiece W where the laser light LB should be emitted.

[0028] The laser oscillator 21 emits laser light LB under processing irradiation conditions in a processing step in which the workpiece W is actually processed, and emits laser light LB under, for example, a plurality of judgment irradiation conditions in a processability judgment step in which the processability of the workpiece W is judged. The laser light LB emitted based on the plurality of judgment irradiation conditions is, for example, one that melts but does not penetrate the workpiece W and one that does not exceed the melting point of the material of the workpiece W, and therefore is not used for cutting the workpiece W by the laser processing device 10. The laser light LB under such judgment irradiation conditions may be irradiated by pulse oscillation.

[0029] The laser processing head 22 has a beam control unit 24. The beam control unit 24 has a function of controlling the laser light LB to a condensed beam diameter and divergence angle suitable for the material of the workpiece W. The beam control unit 24 has a collimator lens 24a that receives the laser light LB emitted from the output end of the process fiber 23 and converts it into a parallel beam, and a folding mirror 24b that reflects the nearly parallel beam of laser light LB emitted from the collimator lens 24a downward in the Z-axis direction perpendicular to the X-axis and Y-axis, and that transmits light of a predetermined wavelength.

[0030] The beam control unit 24 also has a processing condenser lens 24c that focuses the laser beam LB reflected by the folding mirror 24b and irradiates the workpiece W with the focused beam, and a dichroic mirror 24d provided above the folding mirror 24b. The folding mirror 24b is coated, for example, with a coating that reflects at least the wavelengths of the laser beam LB and the guide beam GB (e.g., 1080 nm, 650 nm). The dichroic mirror 24d transmits infrared light (infrared rays) of a predetermined wavelength that is transmitted through the folding mirror 24b, out of the radiation contained in the light traveling from the processing side of the workpiece W toward the folding mirror 24b, toward the radiation thermometer 30A, and reflects visible light toward the light receiving unit 31 of the spectrometer 30.

[0031] The laser processing head 22 is provided at its tip with a nozzle 25 having a circular opening 25a for irradiating the workpiece W with the laser beam LB. The nozzle 25 has a nozzle function of injecting a gas flow of a predetermined assist gas pressure supplied from an assist gas supply device onto the workpiece W together with the laser beam LB in order to remove the molten workpiece W. The nozzle 25 is provided detachably on the laser processing head 22.

[0032] The collimator lens 24a, folding mirror 24b, condenser lens 24c, dichroic mirror 24d, and nozzle 25 are fixed in the laser processing head 22 with their optical axes adjusted in advance. A lens drive unit (not shown) that drives the collimator lens 24a in a direction parallel to the optical axis (X-axis direction) to adjust the focal position is provided in the beam control unit 24. To adjust the focal position, the laser processing head 22 itself may be configured to be movable in the Z-axis direction, which is perpendicular to the X-axis and Y-axis directions, by a drive mechanism (not shown).

[0033] The spectroscope 30 is mounted, for example, on a side of the housing of the laser processing head 22 (above the camera 40 in the illustrated example). The spectroscope 30 inputs, at the reflective side of the dichroic mirror 24d on the side of the housing facing the workpiece W, light to be measured that is transmitted through the turning mirror 24b and reflected by the dichroic mirror 24d from the processing side of the workpiece W toward the turning mirror 24b, and receives the light at the light receiving unit 31.

[0034] The spectroscope 30 separates the light of the object to be measured received by the light receiving unit 31 using a diffraction grating or the like, and detects the light intensity (spectrum) for each wavelength. In this way, the spectroscope 30 is configured to be able to measure the emission spectrum generated when the workpiece W is irradiated with the laser light LB. The spectroscope 30 then outputs the detected light intensity (spectrum) for each wavelength as time-series data.

[0035] Specifically, the spectrometer 30 outputs time series data of the spectrum of light to be measured (first emission spectrum) generated in the workpiece W by the laser light LB irradiated onto the workpiece W under the first determination irradiation condition to the PC 50. The spectrometer 30 also outputs time series data of the spectrum of light to be measured (second emission spectrum) generated in the workpiece W by the laser light LB irradiated onto the workpiece W under the second determination irradiation condition to the PC 50. Note that instead of the spectrometer 30, for example, a photodetector having a bandpass filter can be used.

[0036] The radiation thermometer 30A is provided, for example, inside the upper housing of the laser processing head 22, on the transmission side of the dichroic mirror 24d that faces the workpiece W. The radiation thermometer 30A captures infrared light, including infrared light emitted by thermal radiation that has passed through the folding mirror 24b and the dichroic mirror 24d, from electromagnetic waves having a wide band of wavelengths that are emitted from the material of the workpiece W heated by the laser light LB, and converts this infrared light into an electrical signal.

[0037] The radiation thermometer 30A measures the intensity of infrared rays in a wavelength band of 1600 nm or more. That is, the radiation thermometer 30A has, for example, a wavelength filter in the front stage that transmits only wavelengths in a specific band (1600 nm or more and 2500 nm or less), and uses, for example, a photodiode using InGaAs (indium gallium arsenide) as a photoelectric conversion element in the rear stage.

[0038] Specifically, the radiation thermometer 30A measures the infrared intensity of the radiant light generated in the workpiece W by the laser beam LB irradiated onto the workpiece W under the third and fourth judgment irradiation conditions. The output of the radiation thermometer 30A is converted into time-series data of the infrared intensity via an A / D converter 39 and input to the PC 50. Note that instead of the radiation thermometer 30A, an infrared sensor equipped with an optical lens system (not shown) or the like may be used.

[0039] The camera 40 is attached, for example, to the side of the housing of the laser processing head 22, and is equipped with an optical system 40a having an illumination 40b that illuminates the workpiece W on the processing stage 11. The camera 40 is provided so as to be able to capture an image of at least a portion of the workpiece W, for example, a predetermined range (predetermined imaging range) on the surface.

[0040] The camera 40 can be any type of known camera, as long as it is capable of capturing an image of the surface of the workpiece W and obtaining image information that can be used to determine the surface condition, such as an inexpensive and versatile monocular camera (i.e., a single camera), an optical camera that captures visible light, and a 3D image sensor that transmits and scans laser light and receives reflected light to obtain a three-dimensional distance image as image information.

[0041] In the first embodiment, the camera 40 acquires image information of a predetermined measurement area on the surface of the workpiece W. Therefore, the PC 50 of the first embodiment is configured to determine the surface condition of the predetermined measurement area on the surface of the workpiece W and execute a workability determination process based on the determined surface condition. Examples of the measurement area include an area including a position on the surface of the workpiece W where cutting processing is to be performed, and an area on the surface of the workpiece W that is free of excessive rust, dirt, scratches, etc. and represents the surface condition of the majority of the entire surface.

[0042] The measurement area is, for example, a rectangular area of ​​approximately 20 mm square to approximately 30 mm square. It is advantageous for the image information obtained by capturing an image of the measurement area to have as little data volume as possible, taking into consideration the processing load of machine learning and surface condition determination processing. For this reason, the resolution is set to approximately 196 pixels by approximately 148 pixels, and the image resolution is set to approximately 145 μm. The focal depth is set to approximately ±11 mm so as to be compatible with workpieces W with thicknesses of 19 mm to 40 mm (t19 to t40). The position and size of the measurement area, and the parameters of the image information (resolution, etc.) are not limited to those exemplified above.

[0043] Next, a process for determining the surface state (surface determination) in the machining system 100 configured as above will be described.

[0044] Fig. 2 shows an example of time-series data based on the measurement results of the emission spectrum generated when a workpiece is irradiated with laser light under the judgment irradiation conditions, measured with a spectrometer. Fig. 2 shows the time-series data for each wavelength, particularly the time-series data for the 800 nm band, with the horizontal axis representing time (milliseconds) and the vertical axis representing the amplitude of the emission intensity in arbitrary units (arb.u.).

[0045] The first determination irradiation conditions are conditions suitable for evaluating the surface quality of the workpiece W when determining the workability of the workpiece W, and the laser output is smaller than the laser output (7000 W to 8000 W) of the processing irradiation conditions. The first determination irradiation conditions in the first stage described below are, for example, a laser output of the laser light LB of 1000 W and a laser irradiation time of 0.5 seconds (500 ms) from the start of laser (Laser ON).

[0046] In the illustrated example, the time series data for the second judgment irradiation conditions (conditions suitable for evaluating the internal quality of the workpiece W (e.g., the proportion of impurities, etc.)) in the second stage described below, in which the laser output of the laser light LB is 1400 W and the laser irradiation time is 2.0 seconds (2000 ms) from 500 ms onwards until the laser ends (e.g., 2500 ms), are also shown; however, the judgment of workability will be described later, so a detailed description will be omitted here.

[0047] In addition, the output frequency of the laser light LB under each judgment irradiation condition is, for example, 1000 Hz, the duty is 100%, the assist gas type is air, the gas pressure is 0.1 MPa, and the nozzle gap is 50 mm. As shown in Figure 2, it has been found that the reaction of the surface condition of the workpiece W appears in the time waveform of the time series data from the start of laser irradiation to about 0.2 seconds (reaction time).

[0048] 3 is a diagram showing an example of a processing quality evaluation result that allows comparison between time waveforms of time-series data of reaction times, which show different surface conditions for each workpiece material, and surface images including processing marks. As shown in FIG. 3, in the processing quality evaluation result 220 of a workpiece W made of mild steel with a plate thickness of 19 mm, for example, the quality evaluations of processing quality, "○", "△", and "×", are defined by actually checking and evaluating the material surface of the workpiece W from the viewpoint of workability, and represent "good", "slightly poor", and "poor", respectively.

[0049] In the case of the material (Material A) of the workpiece W made by Manufacturer A, the surface image taken by camera 40 shows that, for example, the adhesion of the oxide film is good, the surface roughness is low, and the processing marks are clean, so the processing quality is "○" and the processability is good. The time waveform of the time series data of the reaction time of this Material A peaks at the moment the laser starts and then stabilizes.

[0050] On the other hand, in the case of the material (Material B) of the workpiece W of Manufacturer B, according to the surface image taken by the camera 40, for example, the oxide film is extremely thin, rust has occurred, the surface is rough, and the processing marks are somewhat irregular, so the processing quality is "△" and the machinability is somewhat poor. The time waveform of the time series data of the reaction time of this Material B does not peak from the start of the laser, and then becomes a waveform that fluctuates.

[0051] In the case of the material (material C) of the workpiece W of manufacturer C, according to the surface image taken by the camera 40, for example, the oxide film is easily peeled off, the surface is rough, and the processing marks are irregular, so the processing quality is "x" and the machinability is poor. The time waveform of the time series data of the reaction time of this material C is a waveform that fluctuates greatly from the start of the laser.

[0052] FIG. 4 is an explanatory diagram showing time waveforms of time-series data of reaction times for portions of the workpiece W with different surface conditions, along with surface images. As shown in FIG. 4, for example, even if Material A has a processing quality rating of "good" as described above in explanatory diagram 221, its entire surface may contain a mixture of portion a with a good surface condition and portion b with rust. In this case, if workability is determined based on the surface condition of portion a, the time waveform will be a waveform indicating good, as described above. However, if workability is determined based on portion b, the time waveform will be a waveform indicating poor, as described above, even though Material A has a processing quality rating of "good." This results in the workpiece W being erroneously determined to be poor and difficult to process. In other words, it has been found that the partial or overall surface condition of the workpiece W significantly affects the determination of the workability of the workpiece W.

[0053] Therefore, in the processing system 100 of the first embodiment, in order to avoid such erroneous judgment, before judging the workability of the workpiece W, the measurement area of ​​the workpiece W is imaged with the camera 40, and the surface condition is judged based on the image information obtained from the image (checking for damage such as partial rust or scratches on the surface), and then it is determined in advance whether it is appropriate to irradiate the measurement area with laser light LB and judge the workability.

[0054] FIG. 5 is a diagram illustrating surface images showing various surface conditions of a workpiece. The size of the measurement area in FIG. 5 (image capture size) is, for example, 21.5 mm vertically and 28.5 mm horizontally. As shown in FIG. 5(a), a processing mark 222 caused by irradiation with laser light LB is formed on the workpiece W with a diameter of approximately 5 mm and can be imaged as shown. FIG. 5(b) shows a surface image 223 of a workpiece W in good surface condition, with almost no rust or peeling of the coating.

[0055] Fig. 5(c) shows a surface image 224 of a workpiece W with a partially poor surface condition, with scattered rust 224a. Fig. 5(d) shows a surface image 225 of a workpiece W with a poor surface condition, with scattered coating peeling 225a. As is clear from the images shown in Figs. 4 and 5, the surface images 223 to 225 captured by camera 40 differ depending on the surface condition of the workpiece W, and the state of the processing marks 222 also changes.

[0056] The processing system 100 is configured to determine the surface condition of the workpiece W before determining its workability based on a surface determination model 5 (Figure 7) created by machine learning using image information 1 (Figure 7) of the surface image of the workpiece W captured by the camera 40 and displayed as shown above as an explanatory variable and surface quality evaluation result 2 (Figure 7) indicating the surface condition of the workpiece W as a target variable.

[0057] FIG. 6 is a schematic functional block diagram of the machining system. 6, the PC 50 constitutes a machinability determination system 100A, and includes a determination model storage unit 51, a machinability calculation unit 52, a machinability determination unit 53 (machinability determination device), and a surface determination unit 54 (surface determination device). The NC device 60 includes a control unit 61 and a machining condition storage unit 62.

[0058] The judgment model storage unit 51 of the PC 50 readably stores a plurality of judgment models (not shown) for evaluating machining conditions according to the surface condition and internal condition of the workpiece W. The machining conditions evaluated in the judgment of machinability are stored in advance in the machining condition storage unit 62 of the NC device 60, for example.

[0059] The workability calculation unit 52 executes various calculation processes related to the determination of the workability of the workpiece W based on information from the spectrometer 30 (time-series data of the emission spectrum) and a plurality of determination models read out from the determination model storage unit 51. The workability determination unit 53 determines and decides the workability of the workpiece W based on the spectrometer 30 and recommended processing conditions based on the calculation results obtained by the workability calculation unit 52, and obtains a determination result (first determination result).

[0060] The processing conditions include, for example, various laser cutting processing conditions (laser output (peak power, repetition frequency, pulse width), machining velocity, focus position, etc.) according to the material (mild steel, stainless steel, blast furnace material, electric furnace material, etc.) and thickness (19 mm, 22 mm, etc.) of the workpiece W. In addition, the energy density per unit time applied to the workpiece W can be determined by parameters such as the above processing conditions (laser output (average laser output), focus position (focus diameter), and processing speed).

[0061] The processability calculation unit 52 can also convert the instantaneous voltage value of the output signal from the radiation thermometer 30A into infrared light intensity and acquire time-series data of this light intensity. The processability calculation unit 52 extracts feature information representing the temporal transition of temperature characteristics based on the acquired time-series data of light intensity. The processability calculation unit 52 also functions as, for example, a signal processing unit.

[0062] That is, the output signal of the current output captured by the radiation thermometer 30A and photoelectrically converted is transmitted to the machinability calculation unit 52. The transmitted output signal is converted into a voltage signal by a current-voltage conversion circuit (not shown). The output signal converted into a voltage signal is then converted into a digital signal by the A / D converter 39 (FIG. 1), and this digital signal is input to the machinability calculation unit 52.

[0063] The machinability determination unit 53 determines a determination result (second determination result) based on the radiation thermometer 30A of the machinability of the workpiece W under the processing conditions of the processing to be performed (the machinability of the workpiece W when cut under processing conditions previously set in the laser processing device 10) based on the feature information extracted by the machinability calculation unit 52 and reference information stored in a storage device (not shown), for example. The reference information is information that is selected and determined, for example, through experiments, and registered in advance.

[0064] Based on a combination of the first judgment result and the second judgment result, the workability judgment unit 53 comprehensively utilizes information obtained by measuring visible light using the spectrometer 30 (such as a quality score of material characteristics) and information obtained by measuring infrared light using the radiation thermometer 30A (such as a quality evaluation of material characteristics), to judge the workability of the workpiece W when cut and processed under preset processing conditions in the processing step, and outputs a comprehensive judgment result (third judgment result).

[0065] The display 70 can display a setting input screen for inputting various information such as cutting conditions, a display screen for displaying various information such as judgment results so that the operator (user) can confirm the information, and the like. The display 70 also functions as a notification unit that notifies the operator (user) of the overall judgment result determined by the machinability judgment unit 53 so that the operator can confirm the information. The display 70 can be configured to include, for example, a touch panel that functions as an input unit. When the display 70 includes a touch panel, the operator (user) can input various information related to the workpiece W to the control unit 61 of the NC device 60, for example, by operating the display 70.

[0066] The surface determination unit 54 receives image information of the measurement area of ​​the workpiece W captured by the camera 40, obtains a surface quality evaluation of the measurement area of ​​the workpiece W, and determines the surface condition. Based on the surface condition evaluation result, the surface determination unit 54 determines the irradiation position of the laser beam LB for machinability evaluation. The irradiation position of the laser beam LB is output to, for example, the control unit 61 of the NC device 60.

[0067] The NC device 60 controls the entire laser processing device 10. A control unit 61 of the NC device 60 outputs control instructions for various operations to, for example, the laser processing head 22 of the laser processing unit 20 that performs cutting, the beam control unit 24, the spectrometer 30, the radiation thermometer 30A, the camera 40, and the PC 50.

[0068] Furthermore, based on the determination result of the processability determination unit 53, the control unit 61 outputs, for example, an instruction to display various information indicating the determination result on the display 70. Note that the control unit 61 can also output notification instructions for various information, such as audio output or lighting, to a speaker or a lamp via an output I / F (Interface) described later.

[0069] The machining condition storage unit 62 stores various machining conditions for the workpiece W in a storage device or the like. Note that, for example, a plurality of machining conditions may be provided in advance in the NC device 60 as standard conditions for standard specifications and machining conditions for difficult-to-machine materials (hereinafter referred to as "difficult-to-machine material conditions") according to the material and thickness of the workpiece W, and may be stored in the machining condition storage unit 62.

[0070] FIG. 7 is a block diagram showing a schematic configuration of a surface determination unit used in the processing system. 7, the surface determination unit 54 according to the first embodiment has a surface determination model 5, and includes a surface condition determination unit 4 that inputs image information 3 obtained by capturing an image of the workpiece W with a camera 40 (imaging device) capable of capturing an image of the workpiece W into the surface determination model 5, determines the surface condition of the workpiece W, and outputs the determination result to a control unit 61 of an NC device 60. The surface determination unit 54 also includes a surface determination model learning unit 6 that creates the surface determination model 5. The surface determination model learning unit 6 functions as a learning device, and inputs image information 1 captured by the camera 40 and a surface quality evaluation result 2 indicating the surface condition of the workpiece W as training data to perform machine learning to create the surface determination model 5.

[0071] The surface determination model learning unit 6 may be provided inside another part of the machining system 100 such as the NC device 60, or may be provided outside the machining system 100.

[0072] Specifically, the two pieces of training data input to the surface determination model learning unit 6 during the learning process are as follows: The first is image information 1 of the workpiece W, which serves as an explanatory variable and is captured by the camera 40, for example, in a measurement area of ​​the workpiece W. The second is surface condition quality evaluation information (e.g., information representing "○", "△", and "×") included in the surface quality evaluation result 2 and serves as a target variable. The surface determination model learning unit 6 inputs the image information 1 and the surface quality evaluation result 2 as training data, performs machine learning based on the input training data, and creates and outputs a surface determination model 5 for determining the surface condition of the workpiece W.

[0073] In the judgment process, the surface condition judgment unit 4 inputs image information 3 of the measurement area of ​​the workpiece W captured by the camera 40 as judgment data, judges the surface condition of the measurement area of ​​the workpiece W based on the surface judgment model 5 created by the surface judgment model learning unit 6, determines the irradiation position of the laser beam LB from the judgment result, and outputs the determined irradiation position to the control unit 61 of the NC device 60. The control unit 61 of the NC device 60 controls each unit of the laser processing device 10 so that the laser beam LB is irradiated at the input irradiation position of the laser beam LB, and performs the next process, the process of judging workability, in cooperation with the PC 50.

[0074] Here, for the machine learning and determination in the surface determination model learning unit 6, various algorithms can be used, such as Random Forest (RF), Regression Analysis (RA), Principal Component Analysis (PCA), Singular Value Decomposition (SVD), Linear Discriminant Analysis (LDA), Independent Component Analysis (ICA), Gaussian Process Latent Variable Model (GPLVM), Logistic Regression (LR), Support Vector Machine (SVM), Discriminant Analysis (DA), Ranking Support Vector Machine (RSVM), Gradient Boosting (GB), Naive Bayes (NB), K-Nearest Neighbor Algorithm (K-NN), and Neural Network (NN), but are not limited to these. In addition, for example, various algorithms used when machine learning the above-mentioned multiple judgment models stored in the judgment model storage unit 51, which are used when judging processability based on information from the spectrometer 30 and the radiation thermometer 30A, may also be similar to those described above.

[0075] [Hardware configuration] Fig. 8 is an explanatory diagram illustrating a basic hardware configuration of a machinability determination system used in a machining system. As shown in Fig. 8, the machinability determination system 100A is realized by hardware including, for example, a GPU (Graphics Processing Unit) 212, a CPU (Central Processing Unit) 201, a RAM (Random Access Memory) 202, a ROM (Read Only Memory) 203, an HDD (Hard Disk Drive) 204, an SSD (Solid State Drive) 205, and a memory card 206.

[0076] The workability determination system 100A also includes, for example, an input I / F (Interface) 207, an output I / F (Interface) 208, and a communication I / F (Interface) 209. The hardware components 201 to 209 are connected to one another via a bus 200.

[0077] The input I / F 207 is connected to input devices 211 including various input devices such as a keyboard, a trackball, a joystick, a mouse, and a touch panel, measuring devices such as a spectrometer 30 and a radiation thermometer 30A, various sensors such as a temperature sensor, an optical sensor, an acoustic sensor, an image sensor, and a spectroscopic sensor, and a camera 40.

[0078] An output device 210 including, for example, a display 70 functioning as a notification unit, and a speaker, lamp, etc. (not shown) is connected to the output I / F 208. The communication I / F 209 communicates with an external device 214 such as a server via a network 213 such as the Internet.

[0079] [Processing system processing flow] FIG. 9 is a flowchart showing an example of a processing flow of the machining system. 9, first, the control unit 61 of the NC device 60 moves the laser processing head 22 on the processing stage 11 to move the camera 40 to the measurement area (step S10). Next, the camera 40 captures a surface image of the workpiece W in the measurement area (step S11), and the acquired image information 3 is sent to the surface determination unit 54 of the PC 50.

[0080] The surface determination unit 54 of the PC 50 inputs image information 3 of the surface image of the workpiece W captured by the camera 40 and transmitted to the surface determination model 5, and performs a surface determination process to determine the surface condition of the workpiece W based on the obtained quality evaluation of the surface condition (step S12).

[0081] Then, in the surface determination process, the surface determination unit 54 determines whether the surface condition of the measurement area of ​​the workpiece W is good (◯) (step S13), and if it is determined that the surface condition is good (Yes in step S13), it determines the measurement area at the time of the determination as the irradiation position of the laser light LB and outputs information about the irradiation position to the control unit 61 of the NC device 60. The control unit 61 irradiates the irradiation position with the laser light LB and executes a workability determination step using, for example, the spectroscope 30 and the radiation thermometer 30A (step S14).

[0082] Then, the control unit 61 of the NC device 60 sets processing conditions in the laser processing device 10 based on, for example, operation input by the operator (user), that are suited to the material state of the workpiece W whose workability has been determined by the workability determination unit 53 in the workability determination process (step S15), and product processing of the workpiece W is carried out based on the set processing conditions (step S16), thereby completing the series of processes according to this flowchart.

[0083] On the other hand, if the surface condition is determined to be poor in step S13 (No in step S13), it can be considered that the quality of the surface condition is partially poor or that the quality of the surface condition is poor. Therefore, the surface determination unit 54 further moves the laser processing head 22 on the processing stage 11 via the control unit 61 of the NC device 60 to move the measurement area measured by the camera 40 (step S17). The measurement area may be moved by moving it horizontally at a movement pitch of a predetermined distance (e.g., 30 mm).

[0084] Then, the surface image of the workpiece W is captured again in the moved measurement area (step S18), and a surface determination process (step S19) is performed to determine whether the number of repetitions of the processes from step S17 to step S19 (for example, 5 times) has reached the upper limit (step S20).

[0085] If it is determined that the number of repetitions has not reached the upper limit (No in step S20), the process proceeds to step S17, where the measurement area is moved a predetermined distance and the subsequent processes are repeated. That is, if the surface determination unit 54 determines that the surface condition of the measurement area of ​​the workpiece W is not good, it determines the surface conditions of each of the other measurement areas on the surface of the workpiece W.

[0086] On the other hand, if it is determined that the number of repetitions has reached the upper limit (Yes in step S20), the variation in the multiple surface condition determination results (e.g., "△" or "X") is checked (step S21), and it is determined whether the variation in the determination results is within a predetermined range (e.g., a predetermined tolerance range) (step S21). If it is determined that the variation in the determination results is within the predetermined range (No in step S21), it may be considered that, for example, rust, peeling, etc. are not present locally on the surface of the workpiece W, but that the surface condition is overall as determined by the multiple determinations in the multiple measurement areas. Therefore, the laser processing head 22 is moved to one of the multiple measurement areas (step S22), or to the last measurement area, and the process proceeds to step S14 above to execute the subsequent processes including the workability determination step.

[0087] Furthermore, if it is determined that the variation in the judgment results exceeds a predetermined range (Yes in step S21), the workpiece W may be considered to be made of a material with an unstable surface condition. Therefore, the laser processing head 22 is moved to the measurement area among the multiple measurement areas that is judged to have the poorest surface condition (poor surface quality) (step S23), and the process proceeds to step S14, where subsequent processing, including the machinability judgment step, is performed. In this case, by performing the machinability judgment step in the measurement area with the poorest surface condition, it is possible to judge the machinability of the workpiece W on the assumption that the material quality (material condition) is poor. In this way, if it is determined that the surface condition of the workpiece W is poor (No in step S13), the PC 50 and the NC device 60 may be configured to irradiate the laser beam LB at an irradiation position of the laser beam LB based on the variation in the judgment results of the multiple measurement areas, and then perform the machinability judgment step.

[0088] [Example of surface determination] Here, an example of the surface determination process in steps S12 and S19 will be described. Fig. 10 is an explanatory diagram showing an example of various surface images representing the surface state of the workpiece W. Fig. 11 is a diagram showing a confusion matrix for explaining the result of surface determination based on the surface determination model.

[0089] In order to verify the surface condition determination in the machining system 100 and the workability determination system 100A, the applicant first captured 100 pieces of image information of the surface image in the measurement region of each of the four samples of workpiece W, obtaining a total of 400 pieces of data. The 400 captured pieces of data were then randomly classified in a ratio of 7:3 into 280 pieces of data for learning (image information 1) and 120 pieces of data for determination (image information 3), and the surface condition was determined 120 times using a surface determination model 5 created by machine learning in a surface determination model learning unit 6.

[0090] Material D shown in FIG. 10(a) is a workpiece W with poor surface quality. Its surface image 226 is captured by, for example, the camera 40, as shown. Materials E and F shown in FIGS. 10(b) and 10(c), respectively, are workpiece W with good surface quality. Their surface images 227 and 228 are captured by, for example, the camera 40, as shown. Material G shown in FIG. 10(d) is a workpiece W with partially poor surface quality. Its surface image 229 is captured by, for example, the camera 40, as shown. The surface determination model learning unit 6 created a surface determination model 5 by machine learning based on learning image information 1 of the surface images 226-229 captured in this way and surface quality evaluation results 2 including information on the surface condition quality evaluation. The result of inputting judgment image information 3 into this surface determination model 5 is shown in FIG. 11.

[0091] In the confusion matrix 230 shown in Figure 11, for material D, 37 judgment data out of 63 training data were correctly identified as material D, with poor surface quality. For material E, 30 judgment data out of 70 training data were correctly identified as material E, and for material F, 28 judgment data out of 72 training data were correctly identified as material F, with good surface quality. For material G, 25 judgment data out of 75 training data were correctly identified as material G, with partially poor surface quality. In other words, the actual surface condition (true label) and the surface condition (predicted label) determined by the surface determination unit 54 matched 100% of the time, which is an extremely high accuracy rate. This proves that the surface determination model 5 can accurately determine the surface condition of all sample workpieces W.

[0092] [Workability determination process] Next, the workability determination step in step S14 will be described. In the workability determination step of this embodiment, for example, the workability determination result from the spectroscope 30 (first determination result) and the workability determination result from the radiation thermometer 30A (second determination result) are combined and used to comprehensively determine the workability of the workpiece W. However, although not described here, the workability determination may be performed based on the determination result from either the spectroscope 30 or the radiation thermometer 30A.

[0093] In the machinability evaluation step, the laser beam LB is irradiated onto the measurement area to which the laser processing head 22 has moved, based on the surface condition evaluation result by the surface evaluation unit 54, with the laser beam LB being set as the irradiation position (any irradiation position within the measurement area) to evaluate the machinability of the workpiece W. In the evaluation using the spectrometer 30, for example, the laser beam LB is irradiated onto the workpiece W under first and second evaluation irradiation conditions that melt but do not penetrate the workpiece W, and the resulting emission spectrum is measured. Note that "melting" as used herein means, for example, generating a molten pool, and "not penetrating" means, for example, not drilling a hole. In the evaluation using the radiation thermometer 30A, for example, the laser beam LB is irradiated onto the workpiece W under third and fourth evaluation irradiation conditions that do not exceed the melting point of the material of the workpiece W, and the infrared intensity of the resulting radiation is measured.

[0094] First, the determination of workability using the spectrometer 30 will be described. The time series data of the emission spectrum measured by the spectrometer 30 is time series data having time series data as shown in FIG. 2 for the number of wavelengths constituting the emission spectrum. The PC 50 performs dimensionality compression on this time series data to extract first waveform information and second waveform information representing feature quantities suitable for machine learning. While various dimensionality compression techniques are conceivable, in this embodiment, data in specific wavelength bands at the start and end of the time series data is compressed. First waveform information for learning and estimation representing feature quantities of the surface condition of the workpiece W is generated based on the time series data in the first time domain in the first stage (laser irradiation time under the first determination irradiation conditions). Furthermore, second waveform information for learning and estimation representing feature quantities of the internal condition of the workpiece W is generated based on the time series data in the second time domain in the second stage (laser irradiation time under the second determination irradiation conditions).

[0095] According to the applicant's verification, it has been found that the time series data in the first time region (e.g., 0 to 0.23 seconds) mainly includes surface condition feature quantities that indicate the reaction between the laser beam LB and the surface (material surface) of the workpiece W. Furthermore, the time series data in the second stage after the first stage indicates the reaction between the laser beam LB and the inside (inside of the material) of the workpiece W, and it has been found that the time series data in the second time region (e.g., from about 1.8 to about 2.3 seconds (1.83 to 2.35 seconds)) includes internal condition feature quantities that indicate the reaction between the laser beam LB and the inside of the workpiece W. These feature quantities vary depending on the material of the workpiece W (differences in material quality, individual differences, etc.).

[0096] Then, first waveform information and second waveform information are calculated based on wavelength components extracted from the time-series data of the first and second emission spectra obtained from the spectrometer 30. It has been found that the calculated first waveform information and second waveform information can be used as data accurately representing the surface condition and internal condition of the workpiece W, respectively.

[0097] The workability calculation unit 52 assigns a quality score to the surface condition and a quality score to the internal condition as a workability evaluation of the workpiece W, for example, based on the judgment model of the surface condition and the internal condition read out from the judgment model storage unit 51 and the first and second waveform information acquired by the spectrometer 30.

[0098] The workability determination unit 53 determines and determines the workability of the workpiece W (e.g., standard material that can be cut well, difficult-to-cut material) and the recommended processing conditions (standard processing conditions, difficult-to-cut material conditions) based on the workability evaluation, which is a combination of the scored surface quality evaluation and internal quality evaluation.

[0099] Next, the determination of workability using the radiation thermometer 30A will be described. Oxygen cutting of a mild steel workpiece W is affected by the surface condition (state of the oxide film) and internal condition of the workpiece W. Even with the same steel type and thickness, the cutting quality varies depending on individual differences such as differences in manufacturer and production lot, even under the same laser cutting processing conditions. The inventors have constructed a processing system 100 and a workability determination system 100A to find, measure, and analyze material property factors that have a strong influence on cutting quality.

[0100] In other words, the oxide film on the material surface (raw material surface) of the workpiece W affects the laser absorption rate and oxidation reaction at the surface. The laser absorption rate varies depending on the type of oxide film. For example, black magnetite has a high laser absorption rate and oxide film adhesion, which stabilizes cutting quality. On the other hand, hematite has a low laser absorption rate and poor oxide film adhesion. For this reason, the oxide film is easily peeled off during laser cutting, and notches are easily created starting from the peeled area.

[0101] Furthermore, in areas where the oxide film is thin or peeled off, oxidation reactions are likely to occur on the surface of the material, which makes excessive combustion more likely to occur on the surface of the material and results in a rough cut surface. From this perspective, the present inventors have found that the adhesion of the oxide film can be determined by the emission spectrum generated immediately after laser irradiation when the surface of the workpiece W is melted with laser light LB.

[0102] For example, the difference between a workpiece W having a highly adhesive oxide film and a workpiece W having a poorly adhesive oxide film, or a thin or peeled oxide film, can be determined by the change over time in the emission spectrum that occurs until the oxide film on the surface (material surface) of the workpiece W disappears.

[0103] In addition, to evaluate the distribution of the oxide film, it is possible to irradiate the material surface with laser light LB within a range that does not melt the material surface, and evaluate the adhesion of the oxide film by the thermal stress generated on the material surface. When the oxide film peels off due to thermal stress, a flash is generated, which can be detected by infrared spectroscopy. In addition, the type and roughness (unevenness) of the oxide film on the material surface cause temperature fluctuations due to differences in laser absorption rate, which can be detected as fluctuations in the infrared spectrum.

[0104] It has also been found that the internal characteristics of the workpiece W are affected by the stability of the melting behavior and the ease of heat transfer (thermal conductivity) due to the internal components of the material other than iron. Regarding the influence of elements other than iron, those with a high carbon content are particularly prone to component segregation, resulting in an uneven carbon concentration distribution and an uneven melting temperature, which can lead to rough cut surfaces due to uneven melting. Manganese, another element that promotes component segregation, can also easily cause unstable melting behavior due to uneven melting.

[0105] Therefore, the stability of the melting behavior affects the temporal change in the emission spectrum that occurs during melting. For example, a high carbon content leads to greater component segregation within the steel sheet, resulting in non-uniformity between the low-melting point and high-melting point areas, and greater fluctuation in the temporal change in the emission spectrum. Furthermore, the greater the amount of elements other than iron contained in the material, the lower the thermal conductivity, making it more likely to become hot at the laser cutting point, which in turn makes it more likely to melt excessively and result in rough cut surfaces.

[0106] Taking the above points into consideration, the processing system 100 and the workability determination system 100A measure the infrared intensity in the wavelength band of 1600 nm or more using a radiation thermometer 30A, and determine the workability of the workpiece W by comparing the information (feature information) in which the temporal change in infrared intensity is used as a feature of the internal state and the positional change is used as a feature of the surface state with a threshold value.

[0107] That is, the machinability calculation unit 52 extracts feature amount information indicating a temporal change in the temperature of the workpiece W as information representing the internal state, based on time-series data of infrared intensity measured by the radiation thermometer 30A of the laser processing unit 20A, and extracts feature amount information indicating a positional change as information representing the surface state. Then, the machinability determination unit 53 determines a determination result of the machinability of the workpiece W from both the internal state and the surface state, based on the extracted feature amount information and reference information for determining the machinability of the workpiece W that has been registered in advance in a storage device or the like (not shown).

[0108] The workability determination unit 53 then makes a comprehensive determination of the workability of the workpiece W based on a combination of the determination result of the workability of the workpiece W by the spectrometer 30 (first determination result) and the determination result of the workability of the workpiece W by the radiation thermometer 30A (second determination result), thereby making it possible, for example, to more appropriately determine the recommended processing conditions according to the predicted workability.

[0109] The workability determination unit 53 can determine the workability (cutability) of the workpiece W, for example, by indicating that the workpiece W is a workpiece material (standard material) that can be laser cut (cutting process) well under standard conditions as the recommended processing conditions. The workability determination unit 53 can also determine the workability of the workpiece W, for example, by indicating that the workpiece W is a workpiece material that can be laser cut (cutting process) under standard conditions but that the standard conditions need to be adjusted (test cut required material). The workability determination unit 53 can also determine the workability of the workpiece W, for example, by indicating that the workpiece W is a workpiece material that is difficult to laser cut (cutting process) under standard conditions as the recommended processing conditions (test cut recommended material). That is, the workpiece W may include standard materials, test cut required materials that can be cut under standard conditions but cannot be cut well, and test cut recommended materials that are difficult to cut under standard conditions. The processing system 100 and the workability determination system 100A can accurately determine the workability suitable for these materials.

[0110] Furthermore, according to the comprehensive determination by the workability determination unit 53, the determination result of the workability of the workpiece W by the spectrometer 30 (first determination result) and the determination result of the workpiece W by the radiation thermometer 30A (second determination result) are used (combined) to comprehensively determine the workability of the workpiece W, thereby making it possible to mutually complement weak points in the determination result by the spectrometer 30 and the determination result by the radiation thermometer 30A. Furthermore, since the processing system 100 and the processability determination system 100A perform a surface determination of the workpiece W before processability determination, it is possible to accurately determine the processability based on the processing conditions of the workpiece W before processing without being affected by the surface state, and it becomes possible to further improve the determination accuracy of the processability (e.g., cuttability).

[0111] In addition, the judgment result of the workability judgment unit 53 is output to the control unit 61 of the NC device 60, so information regarding the judgment result based on the comprehensive judgment (for example, indicating the workability of the workpiece material W as standard material, material requiring test cutting, or material recommended for test cutting) can be displayed on the display 70.

[0112] This allows the operator (user) to more accurately and easily make decisions about what to do (for example, whether to perform cutting under the recommended processing conditions, whether to change or adjust the processing conditions to suit the workpiece W, whether to further adjust the recommended processing conditions, or whether to perform test processing) based on the contents of the processability judgment results (the material state of the workpiece W and the recommended processing conditions). Therefore, since it is possible to accurately and quickly improve the processing quality, the skills of an expert are not required, and it is possible to reduce the occurrence of product defects and the effort required to adjust conditions, thereby making it possible to reduce processing defects.

[0113] [Second embodiment] Fig. 12 is a diagram schematically showing an example of the configuration of a camera in a processing system according to a second embodiment. Figs. 13 and 14 are explanatory diagrams schematically showing an example of installation of a camera in a processing system. Fig. 15 is a flowchart showing an example of a processing flow of the processing system. Note that in the following explanations including Fig. 12, explanations that overlap with parts already explained will be omitted.

[0114] The camera 40 of the processing system 100 of the first embodiment described above was described as capturing an image of a rectangular measurement area of ​​approximately 20 mm square to approximately 30 mm square, but the camera 40 of the processing system 100 of the second embodiment differs in that it is configured to be able to capture an image of a wider area.

[0115] For example, as shown in Fig. 12, the camera 40 mounted on the laser processing unit 20 may be of a type incorporating a galvanometer scanner 41. The galvanometer scanner 41 includes a Y-scan mirror 41a and an X-scan mirror 41b, and controls the laser light LB between a condenser lens 43 and a light-receiving unit 42 to capture an image of the measurement area of ​​the workpiece W. Note that Fig. 12(a) shows an example in which the optical axes of the condenser lens 43 and the light-receiving unit 42 are in the same direction, and Fig. 12(b) shows an example in which the optical axes of the condenser lens 43 and the light-receiving unit 42 form an angle of 90°.

[0116] 13, the camera 40 may be fixedly disposed inside the ceiling 10b of the housing 10a of the laser processing apparatus 10, separate from the laser processing unit 20, to capture an image of the measurement area of ​​the workpiece W on the processing stage 11. Furthermore, as shown in Fig. 14, the camera 40 may be fixedly disposed, for example, outside near the boundary between the ceiling 10b and the side wall 10c of the housing 10a of the laser processing apparatus 10, to capture an image of the measurement area of ​​the workpiece W on the shuttle table 11a installed adjacent to the laser processing apparatus 10. In the case of the fixed arrangement shown in Figs. 13 and 14, the camera 40 itself may be configured to be movable within its imaging range.

[0117] In the case of such a camera 40, the measurement area is moved in step S17 during surface determination by, for example, moving the camera 40 in the configuration shown in Fig. 12 using the range of the angle of view of the camera 40 as a movement pitch, or by moving the imaging range of the camera 40 in the configurations shown in Figs. 13 and 14, and the number of times the process in step S20 is repeated may be set to an upper limit (for example, 2 to 5 times) depending on the size of the workpiece W. With such a configuration, it is possible to determine the surface condition of the workpiece W.

[0118] That is, the camera (imaging device) 40 is provided on one of the laser processing head 22 of the laser processing device 10, the ceiling 10b of the device housing 10a of the laser processing device 10, and the outside of the device housing 10a of the laser processing device 10 so as to be able to image at least a portion of the workpiece W on the processing stage 11 or shuttle table 11a of the laser processing device 10 on which the workpiece W is placed.

[0119] 13 and 14, the entire surface of the workpiece W on the processing stage 11 and the shuttle table 11a may be used as a measurement region to capture a surface image of the workpiece W by the camera 40. In this case, the PC 50 can determine the surface condition of the measurement region covering the entire surface of the workpiece W in a single surface determination process.

[0120] 15, the camera 40 captures a surface image of the workpiece W whose entire surface is in the measurement area (step S30), and the acquired image information 3 is transmitted to the surface determination unit 54 of the PC 50. The surface determination unit 54 of the PC 50 inputs the transmitted image information 3 of the surface image of the workpiece W into, for example, a surface determination model 5 that has learned a surface image that represents the state of the entire surface of the workpiece W, and determines the surface state of the workpiece W based on the obtained quality evaluation of the surface state (step S31).

[0121] Then, in the surface determination process, it is determined whether the overall surface condition of the workpiece W is good (◯), whether the quality of the surface condition is partially poor (△), or whether the quality of the surface condition is poor (×), and the determination result is output to the control unit 61 of the NC device 60. The control unit 61 moves the laser processing head 22 to an irradiation position of the laser light LB set according to the determination result (step S32), and executes the above-described workability determination step using the spectroscope 30 and radiation thermometer 30A (step S33).

[0122] The control unit 61 of the NC device 60 sets processing conditions in the laser processing device 10 that are suited to the material state of the workpiece W whose workability has been determined in the above-mentioned workability determination process (step S34), performs product processing of the workpiece W based on the set processing conditions (step S35), and completes the series of processes according to this flowchart.

[0123] The processing system 100 of the second embodiment can also achieve the same effects as the first embodiment, and when processing a product, the processability based on the processing conditions of the workpiece W can be accurately determined before processing without being affected by the surface condition, so that processing conditions can be set according to the material condition of the workpiece W, and it is easy to know whether processing should be performed under the pre-set processing conditions or whether the processing conditions should be changed to those suitable for the workpiece.

[0124] Although several embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the inventions and their equivalents as defined in the claims.

[0125] For example, in the first embodiment, the surface condition of the workpiece W is determined by determining the surface condition of a predetermined measurement region on the surface of the workpiece W. However, it is also possible to configure the system such that, for example, the entire surface of the workpiece W is imaged for each predetermined measurement region by the camera 40, the surface of the workpiece W is scanned overall in advance, and then the surface condition for each measurement region is determined, or the surface condition of an arbitrary measurement region is determined, and the irradiation position of the laser light LB for determining the workability is determined. [Explanation of symbols]

[0126] 1. Image information (teaching data for explanatory variables) 2. Surface quality evaluation results (training data for objective variables) 3. Image information (data for determining explanatory variables) 5. Surface determination model 6 Surface detection model learning section 10 Laser processing equipment 10a Device housing 11 Processing stage 11a Shuttle Table 20 Laser processing unit 22 Laser processing head 30 spectrometer 30A radiation thermometer 40 Camera 50 Personal Computers (PCs) 51 Decision model storage unit 52 Workability calculation section 53 Workability judgment section 54 Surface determination section 60 NC device 61 Control Unit 62 Processing condition storage section 70 Display 100 Processing System 100A Workability Judgment System

Claims

1. a laser processing device capable of executing a processing step of irradiating a workpiece with laser light under processing irradiation conditions to perform processing, and a processability determination step of irradiating the workpiece with the laser light under determination irradiation conditions that are different from the processing irradiation conditions; an imaging device capable of imaging the workpiece; a surface determination device that determines a surface condition of the workpiece based on image information obtained by imaging the workpiece with the imaging device, and determines an irradiation position of the laser light in the workability determination step based on the determination result of the surface condition of the workpiece; a workability determination device that determines the workability of the workpiece based on light generated by the laser processing device irradiating the laser light onto the irradiation position of the workpiece under the judgment irradiation conditions in the workability determination step; A processing system equipped with

2. the surface determination device has a surface determination model, Image information captured by the imaging device is input to the surface determination model as data for determining the surface condition, and a surface quality evaluation of the workpiece is obtained to determine the surface condition. The processing system of claim 1 .

3. The surface determination model is created by performing machine learning using the image information and the surface quality evaluation results indicating the surface condition of the workpiece as training data. The processing system according to claim 2 .

4. The surface determining device determines the surface condition of a predetermined measurement area on the surface of the workpiece. The processing system of claim 1 .

5. When the surface condition of the measurement area of ​​the workpiece is determined to be good, the surface determination device sets the irradiation position of the laser light in the workpiece in the processability determination step. The processing system according to claim 4.

6. When the surface condition of the measurement area of ​​the workpiece is determined to be poor, the surface determination device determines the surface conditions of the other measurement areas on the surface of the workpiece. The processing system according to claim 4.

7. When it is determined that the variation in the determination results of the plurality of measurement regions is within a predetermined range, the surface determination device sets the irradiation position of the laser light in any one of the plurality of measurement regions in the processability determination step. The processing system according to claim 6.

8. When it is determined that the variation in the determination results of the plurality of measurement areas exceeds a predetermined range, the surface determination device sets the irradiation position of the laser light in the processability determination step to the measurement area among the plurality of measurement areas that is determined to have the worst surface condition. The processing system according to claim 6.

9. a surface determination device that determines a surface condition of the workpiece based on image information obtained by imaging the workpiece with an imaging device capable of imaging the workpiece, and determines an irradiation position of the laser light based on the determination result of the surface condition of the workpiece; a workability determination device that determines the workability of the workpiece based on light generated by irradiating the laser light at the irradiation position of the workpiece under a determination irradiation condition different from the processing irradiation condition; A workability assessment system equipped with

10. The surface determination device is a surface determination model; a learning device for creating the surface determination model; Equipped with inputting image information captured by the imaging device into the surface determination model as data for determining the surface condition, obtaining a surface quality evaluation of the workpiece, and determining the surface condition; The learning device The image information and the surface quality evaluation results showing the surface condition of the workpiece are input as training data, and machine learning is performed to create a surface judgment model. The processability determination system according to claim 9.

Images