Processing device and method for generating trained model

The processing device uses a machine-learning based learned model to accurately assess component states, addressing imaging variability issues and improving operational efficiency.

JP2024158047APending Publication Date: 2024-11-08DISCO CORP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2023072887
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-27
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing processing devices face challenges in accurately determining the state of components such as transport units due to variations in imaging conditions, leading to non-uniform images and increased effort and cost for complex image processing, which hinders efficient operation.

Method used

A processing device equipped with an imaging unit and a learned model configured by machine learning to output a determination result for the state of components, allowing for precise state assessment without complex image processing.

Benefits of technology

Enables easy and precise determination of component states by appropriately extracting features from images, enhancing operational efficiency and preventing erroneous processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158047000001_ABST
    Figure 2024158047000001_ABST
Patent Text Reader

Abstract

To provide a processing device capable of determining the state of a component easily and with high accuracy.SOLUTION: A processing device for processing an object includes an imaging unit that captures images of specific components that constitute the processing device, and a controller that includes a trained model configured by machine learning to output a determination result indicating the state of the components when an image of the components captured by the imaging unit is input.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a processing device that performs processing such as machining on an object, and a method for generating a trained model that determines the state of the processing device. [Background technology]

[0002] A wafer on which a plurality of devices are formed is divided and diced into individual chips, thereby manufacturing a plurality of chips (device chips) each including a device. A package substrate is formed by mounting a plurality of device chips on a predetermined substrate and covering and sealing the mounted device chips with a resin layer (mold resin). A package substrate is divided and diced into individual chips, thereby manufacturing a plurality of chips (packaged devices) each including a plurality of packaged device chips. The device chips and package devices are incorporated into various electronic devices such as mobile phones and personal computers.

[0003] When an object (workpiece) such as a wafer or package substrate is made into chips, the object is processed by various processing devices. For example, the object is processed by processing devices such as a cutting device or a laser processing device, and divided into a plurality of chips. Furthermore, before dividing the object, the object is processed and thinned by processing devices such as a grinding device or a polishing device, thereby obtaining thin chips. Furthermore, before and after processing the object, the object may be cleaned using a cleaning device, or inspected using an inspection device.

[0004] Processing devices such as processing devices, cleaning devices, and inspection devices are composed of various components such as a holding table that holds the object, a transport unit that transports the object, and a processing unit that performs a predetermined process on the object. The operation of each component of the processing device is controlled by a controller to perform a predetermined process on the object. For example, Patent Document 1 discloses a semiconductor manufacturing device that detects the position of a working part based on an image and drives and controls the working part based on the detection result. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 9-167020 Summary of the Invention [Problem to be solved by the invention]

[0006] When processing objects such as wafers and package substrates in processing equipment such as processing equipment, cleaning equipment, and inspection equipment, the status of the components constituting the processing equipment may be monitored so that the series of processing operations of the objects by the processing equipment proceeds appropriately. For example, the processing equipment is equipped with a transport unit that transports the objects, and the status of the transport unit (presence or absence of damage, appropriateness of settings, etc.) is inspected at a predetermined timing. This keeps the transport unit in a state where it can transport the objects appropriately, and prevents erroneous transport of the objects.

[0007] The state of the components of the processing device is determined based on an image acquired by, for example, capturing an image of the components with an imaging unit (camera). However, due to variations in the position and angle of the components when capturing images, variations in the imaging characteristics of the imaging unit, variations in the amount of light and color of the lighting that illuminates the components, and the like, variations may occur in the image patterns, shading, and the like of the components contained in the images. Furthermore, the images of the components may change due to deterioration of the components over time (scratches, discoloration, and the like).

[0008] As described above, in a processing device in which components are imaged under various imaging conditions, the images of the components obtained are often not uniform, making it difficult to determine the state of the components with high accuracy by uniform image processing. On the other hand, if individual image processing is performed according to the imaging conditions, the effort and cost required for reconfiguring the image processing algorithm and optimizing parameters increases. In addition, when actually determining the state of the components, the time required for image processing is extended, which hinders smooth processing of the target object by the processing device.

[0009] The present invention has been made in consideration of such problems, and aims to provide a processing device and a method for generating a trained model that can determine the state of a component easily and with high accuracy. [Means for solving the problem]

[0010] According to one aspect of the present invention, there is provided a processing device for processing an object, the processing device comprising: an imaging unit that images a specific component that constitutes the processing device; and a controller including a trained model configured by machine learning to output a judgment result indicating a state of the component when an image of the component acquired by the imaging unit is input.

[0011] Preferably, the component is a transport unit that transports the object. Also, preferably, the trained model is a neural network including an input layer to which an image of the component is input, and an output layer that outputs the determination result. Also, preferably, the processing device further includes an alarm unit that alarms the determination result when the determination result indicates that the state of the component is abnormal.

[0012] According to another aspect of the present invention, there is provided a method for generating a trained model for determining the state of a processing device that processes an object, the method including: an image collection step of collecting images for each state of predetermined components that constitute the processing device as training images; and a learning step of generating a trained model by machine learning using the training images, which outputs a determination result indicating the state of a component when an image of the component is input.

[0013] Preferably, in the image collecting step, a plurality of first learning images corresponding to images of the component in a normal state and a plurality of second learning images corresponding to images of the component in an abnormal state are collected as the learning images by imaging the component. Also, preferably, the component is a transport unit that transports the object. Effect of the Invention

[0014] A processing device according to one aspect of the present invention includes a trained model configured by machine learning so as to output a determination result indicating the state of a component of the processing device when an image of the component is input. This makes it possible to appropriately extract features from images of various components without performing complex image processing, and to easily and accurately determine the state of the component. [Brief description of the drawings]

[0015] [Figure 1] FIG. [Diagram 2] FIG. [Diagram 3] FIG. [Figure 4] FIG. 2 is a block diagram showing a controller. [Diagram 5] 1 is a flowchart showing a method for generating a trained model. [Figure 6] Figure 6(A) is an image diagram showing an image obtained by imaging a transport unit in a normal state under normal imaging conditions, Figure 6(B) is an image diagram showing an image obtained by imaging a transport unit in a normal state from an angle different from the normal imaging conditions, and Figure 6(C) is an image diagram showing an image obtained by imaging a transport unit in a normal state under an environment different from the normal imaging conditions. [Figure 7] Figure 7(A) is an image diagram showing an image obtained by imaging a transport unit with the transport pad in an inappropriate position, Figure 7(B) is an image diagram showing an image obtained by imaging a transport unit with a missing transport pad, and Figure 7(C) is an image diagram showing an image obtained by imaging a transport unit with individual pieces attached to the transport pad. [Figure 8] FIG. 1 is a block diagram showing a trained model generated by machine learning. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, an embodiment according to one aspect of the present invention will be described with reference to the accompanying drawings. First, a configuration example of a processing device according to this embodiment will be described. FIG. 1 is a perspective view showing a cutting device 2. The cutting device 2 is a processing device that cuts an object with an annular cutting blade. In FIG. 1, the X-axis direction (processing feed direction, front-back direction, first horizontal direction) and the Y-axis direction (indexing feed direction, left-right direction, second horizontal direction) are perpendicular to each other. Also, the Z-axis direction (height direction, up-down direction, vertical direction) is perpendicular to the X-axis direction and the Y-axis direction.

[0017] The cutting device 2 includes a rectangular parallelepiped base 4 that supports or houses each of the components that make up the cutting device 2. A rectangular opening 4a is provided at a corner on the front end side of the base 4. A cassette support table 6 that is raised and lowered by a lifting mechanism (not shown) is provided inside the opening 4a.

[0018] A cassette 8 capable of accommodating a plurality of objects (workpieces) 11 to be processed by the cutting device 2 is placed on the upper surface of the cassette support table 6. The objects 11 correspond to workpieces to be cut by the cutting device 2. Note that in Fig. 1, only the outline of the cassette 8 is shown by a dashed line.

[0019] 2 is a perspective view showing an object 11. For example, the object 11 is a disk-shaped substrate (wafer) made of a semiconductor material such as single crystal silicon, and has a front surface (first surface) 11a and a back surface (second surface) 11b that are generally parallel to each other. The object 11 is divided into a plurality of rectangular regions by a plurality of streets (planned division lines) 13 arranged in a lattice pattern so as to intersect with each other.

[0020] Devices 15 such as ICs (Integrated Circuits), LSIs (Large Scale Integration), LEDs (Light Emitting Diodes), MEMS (Micro Electro Mechanical Systems) devices, etc. are formed on the front surface 11a side of the multiple regions partitioned by the streets 13. By dividing the target object 11 along the streets 13, multiple chips (device chips) each including a device 15 are manufactured.

[0021] When the object 11 is processed by the cutting device 2, the object 11 is supported by a frame 17 for ease of handling (transporting, holding, etc.) the object 11. The frame 17 is an annular member made of a metal such as SUS (stainless steel), and a circular opening 17a is provided in the center of the frame 17, penetrating the frame 17 in the thickness direction. The diameter of the opening 17a is larger than the diameter of the object 11.

[0022] A circular sheet 19 is fixed to the object 11 and the frame 17. For example, the sheet 19 may be a tape including a circular film-like substrate and an adhesive layer (glue layer) provided on the substrate. The substrate is made of a resin such as polyolefin, polyvinyl chloride, or polyethylene terephthalate. The adhesive layer is made of an epoxy-based, acrylic-based, or rubber-based adhesive. The adhesive layer may be an ultraviolet-curable resin that is cured by irradiation with ultraviolet light.

[0023] With the object 11 placed inside the opening 17a of the frame 17, when the center of the sheet 19 is attached to the back surface 11b of the object 11 and the outer periphery of the sheet 19 is attached to the frame 17, the object 11 is supported by the frame 17 via the sheet 19. Then, the object 11, supported by the frame 17, is stored in the cassette 8 (see FIG. 1).

[0024] There are no limitations on the type, material, shape, structure, size, etc. of the object 11. For example, the object 11 may be a substrate (wafer) made of a semiconductor other than silicon (GaAs, InP, GaN, SiC, etc.), sapphire, glass (quartz glass, borosilicate glass, etc.), ceramics, resin, metal, etc. There are also no limitations on the type, number, shape, structure, size, arrangement, etc. of the devices 15, and the object 11 does not necessarily have to have the devices 15 formed thereon.

[0025] Furthermore, the target object 11 may be a package substrate such as a CSP (Chip Size Package) substrate or a QFN (Quad Flat Non-leaded package) substrate. For example, a package substrate is formed by mounting a plurality of device chips on a predetermined substrate and covering and sealing the mounted device chips with a resin layer (mold resin). By dividing and singulating the package substrate, a plurality of chips (packaged devices) each including a plurality of packaged device chips are manufactured.

[0026] 1, a rectangular opening 4b is provided on the side of the opening 4a, with the longitudinal direction aligned with the X-axis direction. A holding table (chuck table) 10 for holding an object 11 is provided inside the opening 4b. A moving mechanism 12 for moving the holding table 10 along the X-axis direction is connected to the holding table 10.

[0027] The moving mechanism 12 is, for example, a ball screw type moving mechanism, and includes an X-axis ball screw (not shown) arranged along the X-axis direction, and an X-axis pulse motor (not shown) that rotates the X-axis ball screw. The moving mechanism 12 also includes a flat table cover 14 provided to surround the holding table 10. At the front and rear of the table cover 14, bellows-shaped dust-proof and drip-proof covers 16 that are expandable and contractible along the X-axis direction are provided. The table cover 14 and the dust-proof and drip-proof covers 16 are set so as to cover the components of the moving mechanism 12 (X-axis ball screw, X-axis pulse motor, etc.) arranged inside the opening 4b.

[0028] The upper surface of the holding table 10 is a flat surface roughly parallel to the horizontal plane (XY plane) and constitutes a holding surface 10a that holds the object 11. The holding surface 10a is connected to a suction source (not shown) such as an ejector via a flow path (not shown), a valve (not shown), and the like provided inside the holding table 10.

[0029] A rotation drive source (not shown), such as a motor, is connected to the holding table 10 to rotate the holding table 10 around a rotation axis roughly parallel to the Z-axis direction. The holding table 10 also includes a plurality of clamps 18 provided around the periphery of the holding surface 10a. The plurality of clamps 18 grip and fix the frame 17 supporting the object 11.

[0030] A pair of guide rails 20 are provided above the front end of the opening 4b. The pair of guide rails 20 are disposed generally parallel to each other along the Y-axis direction, and approach and move away from each other along the X-axis direction. Each of the pair of guide rails 20 includes a support surface that supports the lower side of the frame 17, and a clamping surface that protrudes upward from the support surface and contacts the outer periphery of the frame 17. The pair of guide rails 20 align the object 11 and the frame 17 by clamping the frame 17 placed on the support surface between the clamping surfaces.

[0031] A gate-shaped first support structure 22 is disposed on the upper surface of the base 4 so as to straddle the opening 4b. A rail 24 is fixed along the Y-axis direction on the surface (front surface) side of the first support structure 22. A transport unit (transport mechanism, transport device) 26 that transports the object 11 is attached to the rail 24.

[0032] The transport unit 26 includes a moving part (moving mechanism) 28 mounted on the rail 24, and a holding part (holding mechanism) 30 connected to the moving part 28 and holding the object 11. The transport unit 26 transports the object 11 between the cassette 8 and the pair of guide rails 20, and between the pair of guide rails 20 and the holding table 10.

[0033] The moving unit 28 moves the holding unit 30 in the Y-axis direction by moving along the rail 24. The moving unit 28 also includes an air cylinder. The air cylinder includes a cylinder case and a columnar piston rod housed in the cylinder case. The piston rod is disposed along the Z-axis direction, and the holding unit 30 is fixed to the lower end of the piston rod. When the air cylinder is operated, the piston rod moves (raise and lower) along the Z-axis direction together with the holding unit 30.

[0034] For example, the holding unit 30 includes a plurality of suction pads for holding the frame 17. The lower surfaces of the suction pads form a holding surface for suction-holding the upper surface side of the frame 17. The holding surface of the suction pad is connected to a suction source (not shown) such as an ejector via a flow path (not shown), a valve (not shown), and the like formed inside the holding unit 30. In addition, a gripping unit (gripping mechanism) 30a for gripping the frame 17 is provided at the end of the holding unit 30 on the opening 4a side (cassette 8 side).

[0035] Further, a rail 32 is fixed along the Y-axis direction on the surface (front surface) side of the first support structure 22. A transport unit (transport mechanism, transport device) 34 that transports the object 11 is attached to the rail 32.

[0036] The transport unit 34 includes a moving part (moving mechanism) 36 mounted on the rail 32, and a holding part (holding mechanism) 38 connected to the moving part 36 and holding the object 11. The transport unit 34 transports the object 11 between the holding table 10 and the cleaning unit 50, and between the cleaning unit 50 and the pair of guide rails 20. The configurations of the moving part 36 and the holding part 38 are similar to those of the moving part 28 and the holding part 30 of the transport unit 26, respectively. The configuration of the transport unit 34 will be described in detail later (see FIG. 3).

[0037] A gate-shaped second support structure 40 is disposed behind the first support structure 22 so as to straddle the opening 4b. Ball screw type moving mechanisms 42A and 42B are provided at both ends of the surface (front) side of the second support structure 40. Processing units (machining unit, cutting unit) 44A and 44B that perform cutting on the target object 11 are fixed to the lower parts of the moving mechanisms 42A and 42B, respectively.

[0038] Each of the processing units 44A and 44B includes a cylindrical spindle (not shown) arranged along the Y-axis direction. An annular cutting blade 46 is attached to the tip of the spindle, and a rotation drive source such as a motor is connected to the base end of the spindle. By rotating the spindle with the rotation drive source, the cutting blade 46 rotates around a rotation axis that is approximately parallel to the Y-axis direction.

[0039] For example, a hub-type cutting blade (hub blade) is used as the cutting blade 46. The hub blade has an annular hub base made of a metal such as an aluminum alloy, and an annular cutting edge formed along the outer periphery of the hub base. The cutting edge of the hub blade is formed by an electroformed grinding wheel containing abrasive grains made of diamond, cubic boron nitride (cBN), or the like, and a binder such as a nickel plating layer that fixes the abrasive grains.

[0040] However, a washer-type cutting blade (washer blade) may also be used as the cutting blade 46. A washer blade is composed only of an annular cutting edge containing abrasive grains and a binder made of metal, ceramics, resin, or the like that fixes the abrasive grains.

[0041] The moving mechanism 42A moves the processing unit 44A along the Y-axis direction and the Z-axis direction. This adjusts the position of the cutting blade 46 attached to the processing unit 44A in the Y-axis direction and the Z-axis direction. Similarly, the moving mechanism 42B moves the processing unit 44B along the Y-axis direction and the Z-axis direction. This adjusts the position of the cutting blade 46 attached to the processing unit 44B in the Y-axis direction and the Z-axis direction.

[0042] Imaging units 48 are provided at positions adjacent to the processing units 44A and 44B, respectively. The imaging units 48 include an image sensor such as a CCD (Charged-Coupled Devices) sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) sensor, and capture an image of the object 11 held by the holding table 10. There is no limitation on the type of imaging unit 48, and for example, a visible light camera or an infrared camera is used. The image acquired by the imaging unit 48 is used for alignment between the object 11 and the cutting blade 46, etc.

[0043] A circular opening 4c is provided on the side of the opening 4b. A cleaning unit (cleaning mechanism, cleaning device) 50 for cleaning the object 11 is provided inside the opening 4c. The cleaning unit 50 includes a holding table (spinner table) 52 that holds and rotates the object 11, and a nozzle 54 that supplies a cleaning liquid (cleaning liquid) to the object 11 held by the holding table 52.

[0044] The upper surface of the holding table 52 is a flat surface roughly parallel to the horizontal plane (XY plane) and constitutes a holding surface 52a that holds the target object 11. The holding surface 52a is connected to a suction source (not shown) such as an ejector via a flow path (not shown), a valve (not shown), and the like provided inside the holding table 52. In addition, a rotation drive source (not shown) such as a motor that rotates the holding table 52 around a rotation axis roughly parallel to the Z-axis direction is connected to the holding table 52.

[0045] The nozzle 54 supplies the cleaning liquid toward the holding table 52. As the cleaning liquid, a liquid such as pure water, a mixed fluid in which a liquid (such as pure water) and a gas (such as air) are mixed, or the like can be used.

[0046] The cutting device 2 is also equipped with an imaging unit for monitoring that images one or more components selected from the components (such as the base 4 to the cleaning unit 50) that make up the cutting device 2. Images of the components are acquired by imaging the predetermined components with the imaging unit, and the states of the components are monitored based on the images of the components.

[0047] For example, an imaging unit 58 is installed via a columnar support member 56 at an upper corner portion on the surface (front surface) side of the first support structure 22. A base end portion of the support member 56 is fixed to the surface of the first support structure 22, and the imaging unit 58 is attached to a tip portion of the support member 56. Examples of the configuration and type of the imaging unit 58 are similar to those of the imaging unit 48.

[0048] The imaging unit 58 captures an image of the transport unit 34 from above, and obtains an image of a part or the entire transport unit 34. Then, the state of the transport unit 34 is determined based on the image of the transport unit 34 obtained by the imaging unit 58. Details of the determination of the state of the transport unit 34 will be described later (see FIG. 4).

[0049] The imaging unit 58 is preferably a camera capable of changing the imaging area and magnification. A moving mechanism for moving the imaging unit 58 may be connected to the imaging unit 58. This makes it possible to image any part of the transport unit 34 at any angle and magnification. The imaging unit 58 may also include lighting (light source) for illuminating the subject during imaging. By imaging the transport unit 34 while illuminating it with lighting, a clear image of the transport unit 34 can be obtained.

[0050] However, there are no limitations on the configuration, number, imaging target, installation location, etc. of the imaging units mounted on the cutting device 2. For example, the cutting device 2 may be equipped with multiple imaging units that image the transport unit 34 from different angles. In addition, the cutting device 2 may be equipped with an imaging unit that images components other than the transport unit 34.

[0051] A cover 60 that covers the components of the cutting device 2 is provided on the upper side of the base 4. In Fig. 1, only the outline of the cover 60 is shown by a dashed line. A display unit (display section, display device) 62 that displays various information related to the cutting device 2 is provided on the side of the cover 60. In addition, an alarm unit (alarm section, alarm device) 64 that notifies the operator of information is provided on the upper part of the cover 60.

[0052] For example, a touch panel display is used as the display unit 62. In this case, the display unit 62 also functions as an input unit (input section, input device) for inputting information to the cutting device 2, and the operator can input information such as processing conditions to the cutting device 2 by touching the display unit 62. However, the input unit may be an electronic device such as a keyboard, a mouse, a transceiver, or the like provided separately and independently from the display unit 62.

[0053] As the notification unit 64, for example, an indicator light (warning light) is used. In this case, when an abnormality occurs in the cutting device 2, the notification unit 64 lights up or flashes to notify the operator of the abnormality. However, there is no limit to the type of notification unit 64. For example, the notification unit 64 may be a speaker that notifies the operator of information by sound or voice, or a transmitter that transmits information to the outside of the cutting device 2 by wire or wirelessly. Furthermore, when information to be notified to the operator is displayed on the display unit 62, the display unit 62 also functions as a notification unit.

[0054] The cutting device 2 includes a controller (control unit, control section, control device) 66 that controls the cutting device 2. The controller 66 is connected to each of the components constituting the cutting device 2 (the cassette support base 6, the holding table 10, the moving mechanism 12, the clamp 18, the transport unit 26, the transport unit 34, the moving mechanisms 42A and 42B, the processing units 44A and 44B, the imaging unit 48, the cleaning unit 50, the imaging unit 58, the display unit 62, the notification unit 64, etc.). The controller 66 outputs control signals to the components of the cutting device 2 to control the operation of each component.

[0055] For example, the controller 66 is configured by a computer. Specifically, the controller 66 includes a processing unit that performs processes such as calculations necessary for the operation of the cutting device 2, and a storage unit that stores various information (data, programs, etc.) used for the operation of the cutting device 2. The processing unit includes a processor such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The storage unit includes a memory such as a ROM (Read Only Memory) and a RAM (Random Access Memory).

[0056] When cutting the object 11 with the cutting device 2, a cassette 8 containing a plurality of objects 11 is set on the cassette support table 6, and the objects 11 are carried out one by one from the cassette 8. Specifically, the transport unit 26 grips the frame 17 contained in the cassette 8 with the gripping portion 30a, and moves along the Y-axis direction so as to move away from the cassette 8. As a result, the frame 17 is carried out of the cassette 8 together with the object 11, and is placed on the pair of guide rails 20. Thereafter, the frame 17 is sandwiched between the pair of guide rails 20, and the object 11 and the frame 17 are aligned.

[0057] Next, the transport unit 26 suction-holds the upper surface side of the frame 17 with multiple suction pads, and transports the frame 17 together with the object 11 to the holding table 10. As a result, the object 11 is placed on the holding surface 10a of the holding table 10 via the sheet 19. In addition, the frame 17 is gripped by multiple clamps 18. In this state, when the suction force (negative pressure) of the suction source is applied to the holding surface 10a, the object 11 is suction-held by the holding table 10 via the sheet 19.

[0058] The object 11 held by the holding table 10 is cut by a cutting blade 46 attached to the processing unit 44A or the processing unit 44B. For example, by cutting the object 11 with the cutting blade 46 attached to the processing unit 44A, the object 11 is divided into a plurality of chips.

[0059] Specifically, first, the holding table 10 is rotated to align the length direction of a predetermined street 13 (see FIG. 2) with the X-axis direction. In addition, the position of the processing unit 44A in the Y-axis direction is adjusted so that the cutting blade 46 is positioned on an extension line of the predetermined street 13. Furthermore, the height of the processing unit 44A is adjusted so that the lower end of the cutting blade 46 is positioned lower than the back surface 11b of the target object 11 (the upper surface of the sheet 19).

[0060] Then, while rotating the cutting blade 46, the holding table 10 is moved along the X-axis direction. As a result, the holding table 10 and the cutting blade 46 move relatively along the X-axis direction (processing feed), and the cutting blade 46 cuts into the object 11 along the streets 13. As a result, the object 11 is cut along the streets 13. Thereafter, the same procedure is repeated to cut the object 11 along all the streets 13. As a result, the object 11 is divided into a plurality of chips each having a device 15 (see FIG. 2).

[0061] When cutting of the object 11 is completed, the object 11 is transported by the transport unit 34 to the cleaning unit 50, and is suction-held by the holding table 52. Then, the object 11 is cleaned by supplying a cleaning liquid from the nozzle 54 toward the object 11 while rotating the holding table 52.

[0062] When cleaning of the object 11 is completed, the object 11 is placed on the pair of guide rails 20 by the transport unit 34. Then, the frame 17 is sandwiched between the pair of guide rails 20, and the frame 17 is aligned. Thereafter, the transport unit 26 grips the frame 17 with the gripping portion 30a, and moves along the Y-axis direction so as to approach the cassette 8. As a result, the frame 17 is carried into and stored in the cassette 8 together with the object 11.

[0063] As described above, while the cutting device 2 is in operation, the state of one or more components selected from the components constituting the cutting device 2 (base 4 to cleaning unit 50, etc.) is monitored. This allows an abnormality occurring in the components of the cutting device 2 to be quickly detected, and makes it possible to prevent inappropriate processing of the target object 11. The components to be monitored can be appropriately set while taking into consideration the possibility of abnormality occurrence, etc. Below, as an example, a case where the transport unit 34 is monitored by the imaging unit 58 will be described.

[0064] 3 is a perspective view showing the transport unit 34. As described above, the transport unit 34 includes a moving section 36 and a holding section 38. With the object 11 (see FIG. 2) held by the holding section 38, the moving section 36 moves the holding section 38 along the Y-axis direction and the Z-axis direction, whereby the object 11 is transported.

[0065] The moving part 36 includes a columnar support member 70. A base end of the support member 70 is attached to the rail 32 (see FIG. 1), and an air cylinder 72 is attached to a tip end of the support member 70. The air cylinder 72 includes a cylinder case 74 and a columnar piston rod 76 housed in the cylinder case 74. The piston rod 76 is disposed along the Z-axis direction, and the holding part 38 is fixed to a lower end of the piston rod 76. When the air cylinder 72 is operated, the piston rod 76 moves (raises and lowers) along the Z-axis direction together with the holding part 38.

[0066] The holding unit 38 includes a plate-like base 80 formed in an H-shape in a plan view. The base 80 is configured with a first support plate 82 and a pair of second support plates 84 attached to the first support plate 82. The first support plate 82 is a plate-like member formed in a rectangular shape, and is disposed so that its longitudinal direction is along the X-axis direction. The pair of second support plates 84 are each a plate-like member formed in a rectangular shape, and are attached to both ends of the first support plate 82 so that their longitudinal direction is along the Y-axis direction.

[0067] A pair of suction pads 86 for holding the frame 17 (see FIG. 2) are attached to both ends of the lower surfaces of the pair of second support plates 84, respectively. The lower surfaces of the suction pads 86 form a holding surface for suction-holding the upper surface side of the frame 17. The holding surface of the suction pad 86 is connected to a suction source (not shown) such as an ejector via a flow path (not shown), a valve (not shown), and the like formed inside the holding portion 38. With the holding surface of the suction pad 86 in contact with the upper surface side of the frame 17, the suction force (negative pressure) of the suction source is applied to the holding surface, whereby the frame 17 is sucked and held by the suction pad 86.

[0068] The pair of second support plates 84 are slidably mounted along the first support plate 82, and move in the X-axis direction to approach or move away from each other. The pair of suction pads 86 are slidably mounted along the second support plate 84, and move in the Y-axis direction to approach or move away from each other. By changing the interval between the pair of second support plates 84 and the interval between the pair of suction pads 86, the position of the suction pads 86 is adjusted, and the size of the frame 17 that can be held by the suction pads 86 can be changed. The position of the suction pads 86 may be manually adjusted by an operator, or may be automatically adjusted by an actuator (not shown) mounted on the transport unit 34.

[0069] In this embodiment, the state of the transport unit 34 is determined based on an image acquired by capturing an image of the transport unit 34 with the imaging unit 58 (see FIG. 1). However, due to variations in the position and angle of the transport unit 34 at the time of capturing an image, variations in the imaging characteristics of the imaging unit 58, variations in the amount of light and color of the lighting that illuminates the transport unit 34, and the like, variations may occur in the pattern, shading, and the like of the image contained in the image of the transport unit 34. Furthermore, the image of the transport unit 34 may change due to deterioration over time (scratches, discoloration, and the like) of the transport unit 34.

[0070] As described above, in the cutting device 2 in which the transport unit 34 is imaged under various imaging conditions, the images of the transport unit 34 obtained are often not uniform, and it is difficult to determine the state of the transport unit 34 with high accuracy by uniform image processing. On the other hand, if individual image processing is performed according to the imaging conditions, the effort and cost required for reconfiguring the image processing algorithm and optimizing parameters increases. In addition, when the state of the transport unit 34 is actually determined, the time required for image processing becomes longer, which hinders smooth processing of the target object 11 by the cutting device 2.

[0071] Therefore, in this embodiment, a trained model configured by machine learning is used so that when an image of the transport unit 34 is input, a determination result indicating the state of the transport unit 34 is output. This makes it possible to appropriately extract features from various images of the transport unit 34 without performing complex image processing, and to easily and highly accurately determine the state of the transport unit 34.

[0072] Fig. 4 is a block diagram showing the controller 66. In addition to a block showing the functional configuration of the controller 66, Fig. 4 also shows a schematic diagram of the transport unit 34, the imaging unit 58, the display unit 62, and the notification unit 64. The state of the transport unit 34 is determined by the controller 66.

[0073] The controller 66 includes a determination section 92 that determines the state of the transport unit 34 based on an image (captured image) 90 of the transport unit 34. When the imaging unit 58 captures an image of the transport unit 34, an image 90 showing a part or the whole of the transport unit 34 is acquired and input to the determination section 92. Then, the determination section 92 determines the state of the transport unit 34 based on the image 90, and outputs the determination result.

[0074] The controller 66 also includes a storage unit 94 capable of storing various types of information (data, programs, etc.), and a notification control unit 96 that controls the notification of information by the display unit 62 and / or the notification unit 64. The storage unit 94 corresponds to a computer-readable non-transitory recording medium including memories such as ROM and RAM. The determination result of the determination unit 92 is output to the storage unit 94 and the notification control unit 96.

[0075] The determination unit 92 includes a trained model 100 that determines the state of the transport unit 34. The trained model 100 is configured by machine learning so as to output a determination result indicating the state of the transport unit 34 when an image 90 is input. There is no limit to the type of trained model 100, and a support vector machine (SVM), logistic regression, k-nearest neighbor method, decision tree, neural network, etc. can be used. As an example, a case where the trained model 100 is a neural network NN will be described below.

[0076] The neural network NN is a hierarchical neural network, and includes an input layer 102 to which data is input, an output layer 104 to which data is output, and a plurality of hidden layers (intermediate layers) 106 provided between the input layer 102 and the output layer 104. The input layer 102, the output layer 104, and the hidden layer 106 each include a plurality of neurons (units, nodes). The neurons in the input layer 102 are connected to the neurons in the first hidden layer 106, and the neurons in the output layer 104 are connected to the neurons in the hidden layer 106, which is the final layer. The neurons in the hidden layer 106 are connected to the neurons in the input layer 102 or the hidden layer 106 of the previous layer, and the neurons in the output layer 104 or the hidden layer 106 of the subsequent layer.

[0077] There are no limitations on the number of neurons included in the input layer 102, output layer 104, and hidden layer 106, the activation function of each neuron, the connection relationships between each neuron, etc. Furthermore, there are no limitations on the number of hidden layers 106. A neural network NN that includes two or more hidden layers 106 can be called a deep neural network (DNN). Furthermore, learning of a deep neural network can be called deep learning.

[0078] The neural network NN is trained so that when an image 90 is input to the input layer 102, the neural network NN outputs a determination result indicating the state of the transport unit 34 from the output layer 104. There are no limitations on the training method of the neural network NN. A specific example of the training method of the neural network NN will be described later (see FIG. 8).

[0079] When determining the state of the transport unit 34, the transport unit 34 is imaged by the imaging unit 58, and an image 90 is acquired. The image 90 is then input to the neural network NN, and the state of the transport unit 34 is determined by inference of the neural network NN. Specifically, calculations using the image 90 as input data are sequentially executed in the input layer 102, hidden layer 106, and output layer 104, and data corresponding to the results of classifying the image 90 according to the state of the transport unit 34 is output from the output layer 104. In this way, the state of the transport unit 34 is automatically determined.

[0080] As described above, since the neural network NN handles the classification problem of the image 90, it is preferable to use a convolutional neural network (CNN) as the neural network NN. In this case, a convolutional layer, a pooling layer, a local contrast normalization (LCN) layer, a fully connected layer, etc. are provided as the hidden layer 106. Then, features of the image 90 are extracted by a convolution operation (generation of a feature map) in the convolutional layer and a pooling process in the pooling layer. Also, an operation for classifying the image 90 is performed in the fully connected layer. Then, a numerical value corresponding to the classification result of the image 90 is output from the output layer 104.

[0081] For example, when the determination unit 92 determines whether the state of the transport unit 34 is normal or abnormal (two-class classification), the output layer 104 can be configured with two neurons to which a softmax function is applied as an activation function. Then, each of the two neurons in the output layer 104 outputs a numerical value corresponding to the probability that the transport unit 34 is normal (normal output value) and a numerical value corresponding to the probability that the transport unit 34 is abnormal (abnormal output value).

[0082] The trained model 100 may be realized by either software or hardware. For example, the calculations in the input layer 102, the output layer 104, and the hidden layer 106 of the neural network NN are described by a program, and the program is stored in the storage unit 94. When the program is read from the storage unit 94 and executed by the controller 66, the computer executes a process of inputting an image 90 of the transport unit 34 to the trained model 100 and a process of executing the calculations of the trained model 100. As a result, the state of the transport unit 34 is determined.

[0083] The judgment unit 92 also includes a judgment result processing unit 108 that processes the result of judgment by the trained model 100. For example, the judgment result processing unit 108 compares the normal output value and the abnormal output value output from the output layer 104 of the neural network NN. If the normal output value is greater than the abnormal output value, the judgment result processing unit 108 outputs a signal indicating that the state of the transport unit 34 is normal (normal judgment signal). On the other hand, if the abnormal output value is greater than the normal output value, the judgment result processing unit 108 outputs a signal indicating that the state of the transport unit 34 is abnormal (abnormal judgment signal). The normal judgment signal and the abnormal judgment signal correspond to the result of judgment by the judgment unit 92.

[0084] However, there is no restriction on the content of the processing by the judgment result processing unit 108. For example, the judgment result processing unit 108 may judge the state of the transport unit 34 by comparing the normal output value and the abnormal output value with a reference value (lower limit value) previously stored in the storage unit 94. Specifically, when the normal output value is equal to or greater than the reference value, the judgment result processing unit 108 outputs a normal judgment signal. On the other hand, when the abnormal output value is equal to or greater than the reference value, the judgment result processing unit 108 outputs an abnormal judgment signal. The reference value to be compared with the normal output value and the abnormal output value can be appropriately set according to the required judgment accuracy. For example, the threshold value is set to 0.6 or more (60% or more), 0.8 or more (80% or more), or 0.9 or more (90% or more).

[0085] If both the normal output value and the abnormal output value are less than the threshold value, the image 90 used for the judgment may be acquired again. Specifically, after changing the imaging conditions of the transport unit 34 (the position, angle of the transport unit 34, the imaging area of ​​the imaging unit 58, magnification, etc.), the imaging unit 58 captures an image of the transport unit 34 again, and the image 90 is acquired again. Then, the judgment unit 92 judges the state of the transport unit 34 based on the newly acquired image 90.

[0086] Furthermore, the judgment result processing unit 108 may output, as a judgment result, either or both of the normal output value and the abnormal output value input from the trained model 100. In this case, the judgment result processing unit 108 may perform a predetermined normalization process on the normal output value and the abnormal output value.

[0087] The image 90 and the information on the determination result output from the determining section 92 are stored in a mutually linked state in the storage section 94. In this way, the determination result of the state of the transport unit 34 is accumulated in the storage section 94.

[0088] Furthermore, when the result of the determination by the determination unit 92 is input to the notification control unit 96, the notification control unit 96 causes the display unit 62 and / or the notification unit 64 to notify the determination result as necessary. Specifically, the notification control unit 96 generates a control signal for causing the display unit 62 to display the determination result of the determination unit 92, and outputs the control signal to the display unit 62. The notification control unit 96 also generates a control signal for causing the notification unit 64 to notify the determination result of the determination unit 92, and outputs the control signal to the notification control unit 96. As a result, the determination result of the determination unit 92 is notified to the operator.

[0089] For example, the display unit 62 displays the status (normal or abnormal) of the transport unit 34 using a character string (message), a code, a figure, a symbol, or the like. The display unit 62 may also display the probability of the status (normal or abnormal) of the transport unit 34 using a number, a graph, or the like. For example, a value corresponding to a normal output value output from the trained model 100 is displayed as a percentage on the display unit 62 as the probability that the transport unit 34 is normal. A value corresponding to an abnormal output value output from the trained model 100 is displayed as a percentage on the display unit 62 as the probability that the transport unit 34 is abnormal.

[0090] Furthermore, the display unit 62 may display the image 90 that was the subject of the judgment, in addition to the state of the transport unit 34 or the probability thereof. In this case, the operator can simultaneously check and compare the image 90 and the judgment result. This allows the operator to check whether the judgment made by the trained model 100 is valid or not based on his / her own judgment.

[0091] When the determination result of the determination section 92 indicates that the state of the transport unit 34 is normal, a control signal is output from the controller 66 to each component of the cutting device 2, and the cutting device 2 continues to process (transport, machining, cleaning, etc.) the target object 11. In addition, a control signal is input from the notification control section 96 to the display unit 62, and information informing the user that the transport unit 34 is normal is displayed on the display unit 62.

[0092] On the other hand, when the judgment result of the judgment section 92 indicates that the state of the transport unit 34 is abnormal, a control signal is output from the controller 66 to each component of the cutting device 2, and the processing of the target object 11 by the cutting device 2 is interrupted. In addition, a control signal is input from the notification control section 96 to the display unit 62 and the notification unit 64, and the display unit 62 displays information informing the user that the transport unit 34 is abnormal, and the notification unit 64 lights up in a color or pattern informing the user of the abnormality of the transport unit 34. This notifies the operator of the abnormality of the transport unit 34, and the operator can take measures according to the nature of the abnormality.

[0093] There is no restriction on the timing for determining the state of the transport unit 34. For example, the imaging unit 58 may capture an image of the transport unit 34 while the transport unit 34 is transporting the object 11 during operation of the cutting device 2, or while the transport unit 34 is waiting without transporting the object 11. Furthermore, when maintenance of the cutting device 2 is performed, the imaging unit 58 may capture an image of the transport unit 34 during the maintenance. Then, an image 90 acquired by capturing the image of the transport unit 34 is input to the determination unit 92, and the state of the transport unit 34 is determined.

[0094] As described above, the cutting device 2 according to this embodiment is equipped with the trained model 100 capable of determining the state of the transport unit 34 based on the image 90 of the transport unit 34. This makes it possible to monitor the state of the transport unit 34, and prevents the target object 11 from being transported by a transport unit 34 in an abnormal state. In addition, since the trained model 100 is configured by machine learning, it is possible to appropriately extract features from the images 90 of the transport unit 34 captured under various imaging conditions and determine the state of the transport unit 34.

[0095] There is no limitation on the method of mounting the trained model 100 on the cutting device 2. For example, the manufacturer of the cutting device 2 generates the trained model 100 and incorporates it into the controller 66, and then provides the cutting device 2 to a user.

[0096] In addition, the manufacturer of the cutting device 2 can provide the cutting device 2 equipped with the trained model 100 to the user after the fact by distributing the trained model 100 to a conventional cutting device (a cutting device not equipped with the trained model 100) used by the user. For example, the manufacturer of the cutting device 2 may distribute a program describing the trained model 100 to the cutting device 2 via a network connected to the cutting device 2 used by the user. In addition, the manufacturer of the cutting device 2 may store a program describing the trained model 100 in a recording medium (optical disk, flash memory, etc.) that is a computer-readable non-transitory recording medium, and provide the recording medium to the user of the cutting device 2.

[0097] By distributing the program using a network or a recording medium as described above, the trained model 100 can be introduced later into the cutting device 2 being used by the user. In addition, when the trained model 100 is updated, the manufacturer of the cutting device 2 may distribute a program describing the updated trained model 100 or data corresponding to the parameters of the updated trained model 100 using a network or a recording medium. In this way, the cutting device 2 equipped with the latest trained model 100 is provided to the user.

[0098] Next, a specific example of a trained model generation method according to the present embodiment will be described. Fig. 5 is a flowchart showing the trained model generation method. The trained model generation method according to the present embodiment includes an image collection step S1 for collecting training images, and a learning step S2 for generating a trained model by machine learning using the training images.

[0099] In the image collection step S1, images for each state of the transport unit 34 are collected as learning images. For example, when the state of the transport unit 34 is determined into two categories, normal and abnormal, the transport unit 34 is imaged by the imaging unit 58, and a plurality of first learning images corresponding to images of the transport unit 34 in the normal state and a plurality of second learning images corresponding to images of the transport unit 34 in the abnormal state are collected as learning images.

[0100] The first learning image is collected by capturing an image of the transport unit 34 in a normal state multiple times with the imaging unit 58 (first learning image collection step). Examples of an image (first captured image, first learning image) 110 of the transport unit 34 in a normal state are shown in Figs. 6(A) to 6(C).

[0101] 6A is an image diagram showing an image 110 (image 110A) obtained by imaging the transport unit 34 in a normal state under normal imaging conditions. When the transport unit 34 in a normal state is imaged by the imaging unit 58 under normal imaging conditions, an image 110A showing a part or the whole of the transport unit 34 (the moving part 36 and the holding part 38) is obtained.

[0102] 6B is an image diagram showing an image 110 (image 110B) acquired by capturing an image of the transport unit 34 in a normal state from an angle different from the normal imaging conditions. For example, the angle of the transport unit 34 or the imaging unit 58 may vary slightly due to vibration, mounting error, or the like. In this case, an image 110B is acquired that shows a part or the whole of the transport unit 34 (movement unit 36 ​​and holding unit 38) at an angle different from that of the image 110A.

[0103] 6C is an image diagram showing an image 110 (image 110C) acquired by capturing an image of the transport unit 34 in a normal state under an environment different from the normal imaging conditions. For example, if the amount of ambient light or the color of the lighting illuminating the transport unit 34 during imaging changes, an image 110C with a different brightness from that of the image 110A is acquired.

[0104] In the first learning image collection step, the transport unit 34 is imaged multiple times by the imaging unit 58 while changing the imaging conditions. This results in the acquisition of multiple different images 110 showing the transport unit 34 in a normal state, as shown in Figures 6(A) to 6(C).

[0105] There is no limitation on the imaging conditions of the transport unit 34. For example, the imaging unit 58 may image the transport unit 34 multiple times while the moving unit 36 ​​moves or raises and lowers the holding unit 38. The moving unit 36 ​​may have a built-in rotation drive source (not shown) such as a motor that rotates the holding unit 38 around a rotation axis roughly parallel to the Z-axis direction. In this case, the imaging unit 58 may image the transport unit 34 multiple times while the holding unit 38 is rotated by the rotation drive source. This allows multiple images 110 showing the transport unit 34 at different positions and / or angles to be acquired.

[0106] Also, the transport unit 34 may be imaged multiple times while changing the magnification or focal position of the imaging unit 58. This allows multiple images 110 with different magnifications or degrees of blurring to be acquired. Furthermore, if the imaging unit 58 is equipped with lighting for illuminating the subject, the transport unit 34 may be imaged multiple times while changing the amount or color of light irradiated from the lighting to the transport unit 34. This allows multiple images 110 with different brightness or saturation to be acquired.

[0107] As described above, in the first learning image collection step, a plurality of images 110 (e.g., 1000 or more) are acquired by capturing images of the transport unit 34 in a normal state a plurality of times. Then, the plurality of images 110 are classified (labeled) as images of the normal transport unit 34, and stored in a predetermined database as first learning images.

[0108] The second learning image is acquired by capturing an image of the transport unit 34 in an abnormal state multiple times with the imaging unit 58 (second learning image collection step). Examples of an image (second captured image, second learning image) 120 of the transport unit 34 in an abnormal state are shown in Figs. 7(A) to 7(C).

[0109] 7A is an image diagram showing an image 120 (image 120A) acquired by imaging the transport unit 34 in a state where the suction pads 86 are in an inappropriate position. As described above, the distance between the pair of second support plates 84 and the pair of suction pads 86 is adjusted according to the size of the object held by the transport unit 34. However, due to malfunction or setting error of the transport unit 34, the multiple suction pads 86 may be positioned at a position different from the position where they should be positioned. When the transport unit 34 in this state is imaged, an image 120A is acquired in which the suction pads 86 are shown at a position different from that of the image 110A (see FIG. 6A).

[0110] 7B is an image diagram showing an image 120 (image 120B) acquired by imaging the transport unit 34 in a state in which the suction pad 86 is missing. When the transport unit 34 repeatedly holds an object, the suction pad 86 may fall off and become missing for some reason. When the transport unit 34 in this state is imaged, an image 120B is acquired showing the transport unit 34 in which the suction pad 86 is missing.

[0111] 7(C) is an image diagram showing an image 120 (image 120C) acquired by imaging the transport unit 34 in a state in which the individual pieces 88 are attached to the suction pad 86. When the transport unit 34 repeatedly holds an object, for some reason, the individual pieces 88, which are part of the object, may not separate from the suction pad 86 and may instead be attached to the suction pad 86. When the transport unit 34 in this state is imaged, an image 120C is acquired that shows the transport unit 34 with the individual pieces 88 attached.

[0112] As described above, in the second learning image collection step, images of the transport unit 34 in an abnormal state are captured multiple times. As a result, multiple different images 120 (e.g., 1000 or more) showing the transport unit 34 in an abnormal state are acquired, as shown in Figs. 7(A) to 7(C). Note that in the second learning image collection step, images of the transport unit 34 may be captured multiple times by the imaging unit 58 while changing imaging conditions, as in the first learning image collection step. Then, the multiple images 120 are classified (labeled) as images of the abnormal transport unit 34, and stored in a predetermined database as second learning images.

[0113] The multiple images 110 acquired in the first learning image collection step correspond to first learning images classified as images of the transport unit 34 in a normal state. Moreover, the multiple images 120 acquired in the second learning image collection step correspond to second learning images classified as images of the transport unit 34 in an abnormal state. That is, by performing the image collection step S1, multiple learning images classified according to the state of the transport unit 34 are collected.

[0114] Although the above describes the case where learning images are acquired by capturing images of the transport unit 34 with the imaging unit 58, there is no limitation on the method of collecting learning images. For example, learning images may be collected by capturing images of the transport unit 34 with another imaging unit provided separately from the imaging unit 58. New learning images may be generated by performing predetermined image processing on the images 110 and 120. Furthermore, the manufacturer of the cutting device 2 may collect learning images by having the user of the cutting device 2 provide images of the transport unit 34.

[0115] Next, a trained model 100 is generated by machine learning using the learning images collected in the image collection step S1, which outputs a determination result indicating the state of the transport unit 34 when an image of the transport unit 34 is input (learning step S2). Fig. 8 is a block diagram showing the trained model 100 generated by machine learning.

[0116] In the learning step S2, supervised learning is performed using the learning images and the classification results of the learning images (the state of the transport unit 34) as teacher data. Specifically, the images 110 and 120 are input as image data to the neural network NN, and the state of the transport unit 34 (normal / abnormal) is input as a correct answer label.

[0117] Then, the parameters of the neural network NN (such as the weights and biases of the neurons) are updated so that the error between the output of the neural network NN and the correct label is reduced. As a result, the neural network NN is reconfigured so that when an image of the transport unit 34 is input to the input layer 102, the neural network NN outputs a determination result of the state of the transport unit 34 from the output layer 104. As a learning algorithm, for example, the backpropagation method can be used. Note that when a CNN is used as the neural network NN, the filter values ​​of the convolution layer, the weights and biases of the neurons of the fully connected layer, etc. are updated by learning using the images 110 and 120 and the state of the transport unit 34 as teacher data.

[0118] As described above, a neural network NN capable of determining the state of the transport unit 34 is generated based on an image of the transport unit 34. Then, the trained neural network NN is stored in the controller 66 (see FIG. 4) of the cutting device 2. In this way, the cutting device 2 equipped with the trained model 100 is obtained.

[0119] The calculations for training the neural network NN may be executed by the controller 66, or may be executed by a large-scale, high-performance computer provided outside the cutting device 2. In the latter case, the trained neural network NN (or parameters of the trained neural network NN) generated outside the cutting device 2 is input to the controller 66 and stored.

[0120] In the above, the trained model 100 judges the state of the transport unit 34 in two stages (normal or abnormal) (see FIG. 4), but the judgment content of the trained model 100 is not limited to this. For example, the trained model 100 may judge the state of the transport unit 34 in three or more stages.

[0121] The trained model 100 may also classify the state of the transport unit 34 by type of abnormality (such as the location or content of the abnormality). In this case, one neuron that outputs the probability that the transport unit 34 is normal and multiple neurons that output the probability that the transport unit 34 is abnormal for each type of abnormality are set in the output layer 104 of the trained model 100. This makes it possible to determine the abnormality of the transport unit 34 in more detail.

[0122] Furthermore, the determination unit 92 (see FIG. 4) of the controller 66 may include a plurality of trained models 100. In this case, the same image 90 may be input to the plurality of trained models 100, or different images 90 may be input to the plurality of trained models 100.

[0123] For example, a plurality of trained models 100 specialized for judging different types of abnormalities are mounted on the judgment unit 92. In this case, one image 90 is input to each of the plurality of trained models 100, and the state of the transport unit 34 is judged for each type of abnormality by the plurality of trained models 100. In addition, when a plurality of types of images 90 with different imaging conditions (position, angle of the transport unit 34, imaging area of ​​the imaging unit 58, magnification, etc.) are acquired, a trained model 100 may be provided for each type of image 90.

[0124] Furthermore, although the above describes a case where the state of the transport unit 34 is determined, the determination unit 92 (see FIG. 4) of the controller 66 can also determine the state of components other than the transport unit 34 among the components (base 4 to cleaning unit 50, etc.) that constitute the cutting device 2. In this case, an imaging unit that captures images of predetermined components other than the transport unit 34 is mounted on the cutting device 2, and a trained model that determines the state of the predetermined components is mounted on the determination unit 92. Then, the trained model determines the state of the predetermined components based on the images of the predetermined components acquired by the imaging unit. Note that the determination unit 92 may be equipped with a plurality of trained models that each determine the state of a different component.

[0125] As described above, the cutting device 2 according to this embodiment includes the trained model 100 configured by machine learning so as to output a determination result indicating the state of the component when an image of the component is input to the cutting device 2. This makes it possible to appropriately extract features from images of various components without performing complex image processing, and to easily and accurately determine the state of the component.

[0126] In the above embodiment, the cutting machine 2 equipped with the trained model 100 has been described, but the trained model according to the present invention can also be installed in processing machines other than cutting machines. Examples of other processing machines that can be equipped with the trained model according to the present invention include grinding machines, polishing machines, laser processing machines, plasma processing machines, etc.

[0127] The grinding device includes a processing unit (grinding unit) that grinds an object (workpiece). The grinding unit includes a spindle, and an annular grinding wheel including multiple grinding stones is attached to the tip of the spindle. The object is ground by rotating the grinding wheel and bringing the grinding stones into contact with the object.

[0128] The polishing device is equipped with a processing unit (polishing unit) that polishes an object (workpiece). The polishing unit is equipped with a spindle, and a disk-shaped polishing pad is attached to the tip of the spindle. The object is polished by rotating the polishing pad and bringing it into contact with the object.

[0129] The laser processing device includes a processing unit (laser irradiation unit) that performs laser processing on an object (workpiece). For example, the laser irradiation unit includes a laser oscillator and a condenser that condenses the laser beam emitted from the laser oscillator. The laser beam emitted from the laser irradiation unit is condensed on the front, back, or inside of the object, thereby performing laser processing on the object.

[0130] The plasma processing apparatus includes a processing unit (gas supply unit) that supplies a gas in a plasma state to an object (workpiece). By supplying the gas in a plasma state from the gas supply unit to the object, the object is subjected to a plasma process such as plasma etching or film formation.

[0131] The trained model according to the present invention can also be mounted on processing devices other than the above-mentioned processing devices. Examples of other processing devices include a cleaning device that cleans an object (object to be cleaned), an inspection device that inspects an object (object to be inspected), a sheet attachment device that attaches a sheet to an object, and a sheet expansion device that applies an external force to the object by expanding a sheet attached to the object.

[0132] The various processing devices as described above are composed of multiple components (holding table, transport unit, processing unit, etc.). The processing device is equipped with an imaging unit that captures images of the predetermined components, and one or more trained models that determine the state of the components based on the images of the components captured by the imaging unit.

[0133] In addition, the structures, methods, etc. according to the above-described embodiments can be modified as appropriate without departing from the scope of the object of the present invention. [Explanation of symbols]

[0134] 11 Object (processing object) 11a Surface (first side) 11b Back side (2nd side) 13th Street (Planned division line) 15 Devices 17 Frame 17a aperture 19 sheets 2 Cutting equipment 4 Foundation 4a,4b,4c opening 6 Cassette Support Stand 8 Cassettes 10 Holding table (chuck table) 10a Holding surface 12 Moving mechanism 14 Table Cover 16 Dust-proof / water-proof cover 18 Clamp 20 Guide rail 22 First support structure 24 Rail 26 Transport unit (transport mechanism, transport device) 28 Moving part (moving mechanism) 30 Holding part (holding mechanism) 30a Gripping part (gripping mechanism) 32 Rail 34 Transport unit (transport mechanism, transport device) 36 Moving part (moving mechanism) 38 Holding part (holding mechanism) 40 Second support structure 42A,42B Moving mechanism 44A, 44B Processing unit (machining unit, cutting unit) 46 Cutting Blade 48 Imaging unit 50 Cleaning unit (cleaning mechanism, cleaning device) 52 Holding table (spinner table) 52a Holding surface 54 Nozzle 56 Support member 58 Imaging unit 60 Cover 62 Display unit (display unit, display device) 64 Notification unit (notification section, notification device) 66 Controller (control unit, control section, control device) 70 Support member 72 Air Cylinder 74 Cylinder case 76 Piston rod 80 Bases 82 1st support plate 84 Second support plate 86 Suction Pad 88 pieces 90 images (captured images) 92 Judgment section 94 Memory section 96 Notification control section 100 pre-trained models 102 Input Layer 104 Output layer 106 hidden layer (intermediate layer) 108 Judgment result processing unit 110, 110A, 110B, 110C Images (first captured image, first learning image) 120, 120A, 120B, 120C Images (second captured image, second learning image)

Claims

1. A processing device for processing an object, an imaging unit for imaging a predetermined component constituting the processing device; A processing device comprising: a controller including a trained model configured by machine learning so as to output a judgment result indicating the state of the component when an image of the component acquired by the imaging unit is input.

2. 2. The processing apparatus according to claim 1, wherein the component is a transport unit that transports the object.

3. 3. The processing device according to claim 1, wherein the trained model is a neural network including an input layer to which an image of the component is input, and an output layer to which the determination result is output.

4. 3. The processing device according to claim 1, further comprising an alarm unit that, when the determination result indicates that the state of the component is abnormal, notifies the user of the determination result.

5. A method for generating a trained model for determining a state of a processing device that processes an object, comprising: an image collection step of collecting images of predetermined components constituting the processing device for each state as learning images; a learning step of generating a trained model by machine learning using the training image, which generates a trained model that outputs a judgment result indicating the state of the component when an image of the component is input.

6. The method for generating a trained model according to claim 5, characterized in that in the image collection step, a plurality of first training images corresponding to images of the component in a normal state and a plurality of second training images corresponding to images of the component in an abnormal state are collected as the training images by imaging the component.

7. The method for generating a trained model according to claim 5 or claim 6, characterized in that the component is a transport unit that transports the object.

Citation Information

Patent Citations

  • Substrate holding member, substrate processing device, method for controlling substrate processing device, and storage medium storing program

    JP2019137898A

  • Integrated hardware and software computer vision system for autonomous control and inspection of substrate processing systems

    JP2022542946A

  • Recognition driving control unit and detection device for moving body

    JP1997167020A