Charged particle beam apparatus

Abstract

The present invention provides a charged particle beam device capable of speeding up automatic micro-sampling. The charged particle beam device is a charged particle beam device that automatically produces a specimen piece from a specimen, and includes: a charged particle beam irradiation optical system that irradiates a charged particle beam; a specimen stage that moves while carrying the specimen; a specimen piece transfer unit that holds and transports the specimen piece separated and extracted from the specimen; a holder fixing stage that holds a specimen piece holder for transferring the specimen piece; and a computer that controls the position related to the second object according to a machine learning model obtained from learning the first information and the second information, wherein the first information includes a first image of a first object, and the second information includes a second image obtained by irradiating the charged particle beam.

Description

Technical Field

[0001] The present invention relates to a charged particle beam apparatus. Background Art

[0002] Conventionally, there has been known a device that extracts a specimen piece produced by irradiating a specimen with a charged particle beam composed of electrons or ions, and processes the specimen piece into a shape suitable for various processes such as observation, analysis, and measurement using a transmission electron microscope (TEM: Transmission Electron Microscope) or the like (Patent Document 1). In the device described in Patent Document 1, the following so-called micro-sampling (MS: Micro-sampling) is performed. That is, in the case of observation using a transmission electron microscope, after taking out a minute thin film specimen piece from a specimen as an object to be observed, the thin film specimen piece is fixed to a specimen holder to produce a TEM specimen.

[0003] There has been known a charged particle beam apparatus that, in the production of a thin specimen for TEM observation, detects an object such as the tip of a microprobe, the pickup position of the thin specimen, and the end of a support on a mesh holder by template matching (Patent Document 2). In the charged particle beam apparatus described in Patent Document 2, position control related to the object is performed based on a template and position information obtained from an image of the object, and the template is produced based on an image of the object obtained by irradiation with a charged particle beam. Thus, in the charged particle beam apparatus described in Patent Document 2, MS (automatic MS) can be automatically performed.

[0004] Prior Art Documents

[0005] Patent Documents

[0006] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2019-102138

[0007] Patent Document 2: Japanese Unexamined Patent Application Publication No. 2016-157671

[0008] In the charged particle beam apparatus described in Patent Document 2, every time position control of the object is performed, it is necessary to acquire a template image, and accordingly, the speed of automatic MS is reduced corresponding to the amount of time for acquiring the image. For example, the tip shape of the microprobe changes due to cleaning or specimen attachment, etc., and thus, every time position control of the object is performed, a template image has to be acquired. In addition, for the template image of the pickup position of the thin specimen, since the matching accuracy decreases due to differences in contrast, focus, etc., a template image has to be acquired before starting position control. In addition, since there are individual differences in the support angles, the user registers the position of the support on the image by mouse operation every time.

[0009] On the other hand, in the charged particle beam apparatus described in Patent Document 2, in order to improve the success rate of template matching, the scanning speed is reduced to obtain a high-definition image.

[0010] Thus, conventionally, the speed of automatic MS has been insufficient, and there has been a demand to increase the speed of automatic MS and improve throughput. Summary of the Invention

[0011] The present invention has been made in view of the above problems, and provides a charged particle beam apparatus capable of increasing the speed of automatic MS.

[0012] To solve the above problems and achieve the above object, the present invention adopts the following means.

[0013] (1) One aspect of the present invention is a charged particle beam apparatus that automatically produces a specimen piece from a specimen, and includes: a charged particle beam irradiation optical system that irradiates a charged particle beam; a specimen stage that moves while carrying the specimen; a specimen piece transfer unit that holds and transports the specimen piece separated and extracted from the specimen; a holder fixing stage that holds a specimen piece holder for transferring the specimen piece; and a computer that controls the position related to the second object based on a machine learning model obtained from learning the first information and the second information, where the first information includes a first image of a first object, and the second information includes a second image obtained by irradiating the charged particle beam.

[0014] In the composite charged particle beam apparatus according to the above (1), the position of the object can be detected based on machine learning, and thus, the speed of automatic MS can be increased. In the charged particle beam apparatus 10, since the position of the object is detected based on machine learning, the time for obtaining a template image each time as in the case of using template matching can be reduced, thereby increasing the speed of automatic MS and improving throughput.

[0015] In a charged particle beam apparatus, conventionally, the scanning speed has been reduced to obtain a high-definition image in order to improve the success rate of template matching. However, in machine learning, even if the image is not high-definition, position detection can be performed. Therefore, the scanning speed at the time of obtaining an image can be increased, the speed of automatic MS can be increased, and throughput can be improved.

[0016] In a charged particle beam apparatus, operations that were conventionally performed manually by a user when creating a processing recipe can be automated, and thus, recipe creation becomes simple. In addition, in a charged particle beam apparatus, it is not necessary to prepare a recipe for each specimen, and thus, a system structure that can withstand shape changes is configured.

[0017] (2) Based on the charged particle beam device described in (1) above, the second object includes a part of the specimen stage included in the specimen holder.

[0018] In the composite charged particle beam device according to the method described in (2) above, since the position of the part of the specimen stage can be detected based on machine learning, in the automatic MS, the process of connecting the specimen piece to the part of the specimen stage can be speeded up.

[0019] (3) Based on the charged particle beam device described in (1) or (2) above, the second object includes the needle used in the specimen piece transfer unit.

[0020] In the composite charged particle beam device according to the method described in (3) above, the position of the tip of the needle can be detected based on machine learning, so in the automatic MS, the process of moving the needle can be speeded up.

[0021] (4) Based on the charged particle beam device described in any one of (1) to (3) above, the second object includes the specimen piece, and the first image is an image showing the position where the specimen piece transfer unit approaches the specimen piece in the specimen extraction process of extracting the specimen piece.

[0022] In the composite charged particle beam device according to the method described in (4) above, the position where the specimen piece transfer unit approaches the specimen piece can be detected based on machine learning in the specimen extraction process of extracting the specimen piece, so in the automatic MS, the process of moving the needle close to the specimen piece can be speeded up.

[0023] (5) Based on the charged particle beam device described in any one of (1) to (4) above, the second object includes the specimen piece, and the first image is an image showing the position where the specimen piece is separated from and extracted from the specimen.

[0024] In the composite charged particle beam device according to the method described in (5) above, the position where the specimen piece is separated from and extracted from the specimen can be detected based on machine learning, so in the automatic MS, the process of connecting the specimen piece to the needle can be speeded up.

[0025] (6) Based on the charged particle beam device described in any one of (1) to (5) above, the first image is a simulation image generated according to the type of the second object.

[0026] In the charged particle beam device according to the method described in (6) above, even when it is impossible to prepare, in sufficient quantities, images obtained by irradiating with an actual charged particle beam as the first images, simulation images can be used in place of these images. Therefore, the accuracy of machine learning for learning the first information can be improved.

[0027] (7) Based on the charged particle beam device described in any one of (1) to (6) above, the type of the first object is the same as the type of the second object.

[0028] In the charged particle beam device according to the method described in (7) above, the position of an object can be detected based on machine learning that has learned the first information, where the first information includes the first image of the first object of the same type as the type of the second object. Therefore, compared with the case where the type of the first object and the type of the second object are different, machine learning can be improved.

[0029] According to the present invention, high-speed automatic micro-sampling can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 FIG. is an example showing the structure of the charged particle beam device and the image processing computer according to the first embodiment of the present invention.

[0031] Figure 2 FIG. is an example showing the structure of the charged particle beam device according to the first embodiment of the present invention.

[0032] Figure 3 FIG. is a top view of the specimen piece according to the first embodiment of the present invention.

[0033] Figure 4 FIG. is a top view of the specimen piece holder according to the first embodiment of the present invention.

[0034] Figure 5 FIG. is a side view of the specimen piece holder according to the first embodiment of the present invention.

[0035] Figure 6 FIG. is an example showing the structure of the image processing computer according to the first embodiment of the present invention.

[0036] Figure 7 FIG. is an example showing the initial setting process according to the first embodiment of the present invention.

[0037] Figure 8 FIG. is a top view of the columnar part according to the first embodiment of the present invention.

[0038] Figure 9 FIG. is a side view of the columnar part according to the first embodiment of the present invention.

[0039] Figure 10 This is a diagram showing an example of a learning image of a columnar part according to the first embodiment of the present invention.

[0040] Figure 11 This is a diagram showing an example of a columnar part in which the support column according to the first embodiment of the present invention does not form a stepped structure.

[0041] Figure 12 This is a diagram showing an example of a learning image of a columnar part in which the support column according to the first embodiment of the present invention does not form a stepped structure.

[0042] Figure 13 This is a diagram showing an example of a sample piece picking process according to the first embodiment of the present invention.

[0043] Figure 14 This is a diagram showing an example of the movement process of a needle according to the first embodiment of the present invention.

[0044] Figure 15 This is a diagram showing an example of SEM image data including the tip of a needle according to the first embodiment of the present invention.

[0045] Figure 16 This is a diagram showing an example of SIM image data including the tip of a needle according to the first embodiment of the present invention.

[0046] Figure 17 This is a diagram showing an example of the tip of a needle according to the first embodiment of the present invention.

[0047] Figure 18 This is a diagram showing an example of a learning image of a needle according to the first embodiment of the present invention.

[0048] Figure 19 This is a diagram showing an example of SIM image data including a sample piece according to the first embodiment of the present invention.

[0049] Figure 20 This is a diagram showing an example of a learning image of a sample piece according to the first embodiment of the present invention.

[0050] Figure 21 This is a diagram showing the cutting position of a sample and the support part of a sample piece in SIM image data according to the first embodiment of the present invention.

[0051] Figure 22 This is a diagram showing an example of a sample piece mounting process according to the first embodiment of the present invention.

[0052] Figure 23 This is a diagram showing an example of the structure of a computer for image processing according to the second embodiment of the present invention.

[0053] Figure 24 This is a diagram showing an example of a bare part according to the second embodiment of the present invention.

[0054] Figure 25 This is a diagram showing an example of a pattern image according to the second embodiment of the present invention.

[0055] Figure 26 This is a diagram showing an example of a simulation image according to the second embodiment of the present invention.

[0056] Figure 27 This is a diagram showing an example of a detection process of a pick-up position according to the second embodiment of the present invention.

[0057] Reference Signs Explanation

[0058] 10, 10a: charged particle beam apparatus; S: specimen; Q: specimen piece; 14: convergent ion beam irradiation optical system (charged particle beam irradiation optical system); 15: electron beam irradiation optical system 15 (charged particle beam irradiation optical system); 12: specimen stage; 18: needle (specimen piece transfer unit); 19: needle drive mechanism (specimen piece transfer unit); P: specimen piece holder; 12a: holder fixing stage; 22: control computer (computer) Detailed Embodiment

[0059] (First Embodiment)

[0060] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Figure 1 This is a diagram showing an example of the structure of the charged particle beam apparatus 10 and the image processing computer 30 according to the present embodiment. The control computer 22 included in the charged particle beam apparatus 10 acquires image data obtained by irradiation with a charged particle beam. Data is transmitted / received between the control computer 22 and the image processing computer 30. The image processing computer 30 determines an object included in the image data received from the control computer 22 based on the machine learning model M. The control computer 22 controls the position related to the object based on the determination result of the image processing computer 30.

[0061] The control computer 22 is an example of a computer that controls the position related to the second object based on the machine learning model obtained by learning the first information and the second information, where the first information includes the first image of the first object, and the second information includes the second image obtained by irradiation with a charged particle beam.

[0062] In addition, the image processing computer 30 may be provided in the charged particle beam apparatus 10.

[0063] Here, refer to Figure 2The structure of the charged particle beam apparatus 10 will be described.

[0064] (Charged Particle Beam Apparatus)

[0065] Figure 2 FIG. 7 is a diagram showing an example of the structure of the charged particle beam apparatus 10 according to the embodiment. The charged particle beam apparatus 10 includes a specimen chamber 11, a specimen stage 12, a stage drive mechanism 13, a focused ion beam irradiation optical system 14, an electron beam irradiation optical system 15, a detector 16, a gas supply unit 17, a needle 18, a needle drive mechanism 19, a detected current detector 20, a display device 21, a control computer 22, and an input device 23.

[0066] The inside of the specimen chamber 11 is maintained in a vacuum state. The specimen stage 12 fixes the specimen S and the specimen holder P inside the specimen chamber 11. Here, the specimen stage 12 includes a holder fixing stage 12a that holds the specimen holder P. The holder fixing stage 12a may be configured to be able to mount a plurality of specimen holders P.

[0067] The stage drive mechanism 13 is for driving the specimen stage 12. Here, the stage drive mechanism 13 is housed inside the specimen chamber 11 in a state of being connected to the specimen stage 12, and shifts the specimen stage 12 relative to a specified axis according to a control signal output from the control computer 22. The stage drive mechanism 13 includes a moving mechanism 13a that moves the specimen stage 12 at least parallel to the X-axis, the Y-axis, and the Z-axis in the vertical direction orthogonal to the X-axis and the Y-axis, where the X-axis and the Y-axis are parallel to the horizontal plane and orthogonal to each other. The stage drive mechanism 13 includes: a tilting mechanism 13b that tilts the specimen stage 12 about the X-axis or the Y-axis; and a rotating mechanism 13c that rotates the specimen stage 12 about the Z-axis.

[0068] The focused ion beam irradiation optical system 14 irradiates an irradiation target within a specified irradiation region (i.e., a scanning range) inside the specimen chamber 11 with a focused ion beam (FIB). Here, the focused ion beam irradiation optical system 14 irradiates an irradiation target such as the specimen S, the specimen piece Q, and the needle 18 existing in the irradiation region placed on the specimen stage 12 with a focused ion beam from vertically above downward.

[0069] The focused ion beam irradiation optical system 14 includes: an ion source 14a that generates ions; and an ion optical system 14b that converges and deflects the ions drawn out from the ion source 14a. The ion source 14a and the ion optical system 14b are controlled according to a control signal output from the control computer 22, and the control computer 22 controls the irradiation position and irradiation conditions of the focused ion beam, etc.

[0070] The electron beam irradiation optical system 15 irradiates an object to be irradiated within a specified irradiation area inside the specimen chamber 11 with an electron beam (EB). Here, the electron beam irradiation optical system 15 can irradiate an object to be irradiated, such as a specimen S fixed on the specimen stage 12, a specimen piece Q, and a needle 18 present in the irradiation area, with an electron beam from above in an inclined direction that is inclined by a specified angle (e.g., 60°) with respect to the vertical direction, downward.

[0071] The electron beam irradiation optical system 15 includes: an electron source 15a that generates electrons; and an electron optical system 15b that converges and deflects the electrons emitted from the electron source 15a. The electron source 15a and the electron optical system 15b are controlled according to a control signal output from the control computer 22, and the control computer 22 controls the irradiation position and irradiation conditions of the electron beam, etc.

[0072] Alternatively, the configurations of the electron beam irradiation optical system 15 and the focused ion beam irradiation optical system 14 can be swapped, with the electron beam irradiation optical system 15 arranged in the vertical direction and the focused ion beam irradiation optical system 14 arranged in an inclined direction that is inclined by a specified angle with respect to the vertical direction.

[0073] The detector 16 is used to detect secondary charged particles (secondary electrons, secondary ions) R that are generated from the object to be irradiated by the irradiation of the focused ion beam or the electron beam. The gas supply unit 17 supplies a gas G to the surface of the object to be irradiated. The needle 18 extracts a minute specimen piece Q from the specimen S fixed on the specimen stage 12, holds the specimen piece Q, and transfers it to the specimen piece holder P. The needle drive mechanism 19 drives the needle 18 to transport the specimen piece Q. In the following content, the needle 18 and the needle drive mechanism 19 are sometimes collectively referred to as the specimen piece transfer unit.

[0074] The absorption current detector 20 detects the inflow current of the charged particle beam flowing into the needle 18 (also referred to as the absorption current), and outputs the detected result as an inflow current signal to the control computer 22.

[0075] The control computer 22 controls at least the stage drive mechanism 13, the focused ion beam irradiation optical system 14, the electron beam irradiation optical system 15, the gas supply unit 17, and the needle drive mechanism 19. The control computer 22 is arranged outside the specimen chamber 11, and is connected to a display device 21 and input devices 23 such as a mouse and a keyboard that output signals corresponding to the input operations of the operator. The control computer 22 centrally controls the operation of the charged particle beam apparatus 10 using the signals output from the input devices 23 or signals generated through preset automatic operation control processing, etc.

[0076] Here, as described above, the control computer 22 controls the position related to the object according to the determination result of the image processing computer 30. The control computer 22 is provided with a communication interface for communicating with the image processing computer 30.

[0077] In addition, the control computer 22 images the inflow current signal output from the absorption current detector 20 into absorption current image data. Here, while scanning the irradiation position of the charged particle beam, the control computer 22 converts the detection amount of the secondary charged particles R detected by the detector 16 into a luminance signal corresponding to the irradiation position, and generates absorption current image data showing the shape of the irradiation object based on the two-dimensional position distribution of the detection amount of the secondary charged particles R. In the absorption current image mode, while scanning the irradiation position of the charged particle beam, the control computer 22 detects the absorption current flowing through the needle 18, and thus generates absorption current image data showing the shape of the needle 18 based on the two-dimensional position distribution (absorption current image) of the absorption current. The control computer 22 causes the generated image data to be displayed on the display device 21.

[0078] The display device 21 displays image data etc. based on the secondary charged particles R detected by the detector 16.

[0079] The charged particle beam apparatus 10 irradiates a converged ion beam while scanning the surface of the irradiation object, and thus can perform imaging of the irradiation object and various processes (such as excavation, trimming process, etc.) by sputtering, deposition film formation, etc.

[0080] Figure 3 It is a plan view of a specimen piece Q before being removed from a specimen S, showing the surface (hatched part) of the specimen S irradiated with a converged ion beam in the charged particle beam apparatus 10 according to an embodiment of the present invention. Reference numeral F represents the processing frame of the converged ion beam, that is, the scanning range of the converged ion beam, and shows the processed area H excavated by sputtering the inner side (white part) thereof by irradiation with the converged ion beam. Reference mark Ref is a reference point showing the position where the specimen piece Q is formed (left without excavation). A deposition film is used to know the approximate position of the specimen piece Q, and a micro hole is used for precise position alignment. In the specimen S, the specimen piece Q is etched in such a manner that a support portion Qa connected to the specimen S is left, and the peripheral portions on the side and bottom sides are cut and removed. The specimen piece Q is cantilever-supported on the specimen S by the support portion Qa.

[0081] Next, with reference to Figure 4 and Figure 5 , the specimen piece holder P will be described.

[0082] Figure 4 It is a plan view of the specimen piece holder P,Figure 5 This is a side view. The specimen holder P includes: a substantially semi-circular plate-shaped base 42 having a cutout portion 41; and a specimen stage 43 fixed to the cutout portion 41. As an example, the base 42 is formed of a circular plate-shaped metal. The specimen stage 43 has a comb shape and includes a plurality of columnar portions (hereinafter also referred to as struts) 44 that are separately arranged and protrude for transferring the specimen piece Q.

[0083] (Computer for image processing)

[0084] Next, refer to Figure 6 and explain the computer 30 for image processing. Figure 6 This is a diagram showing an example of the structure of the computer 30 for image processing according to the present embodiment. The computer 30 for image processing includes a control unit 300 and a storage unit 305.

[0085] The control unit 300 includes a learning data acquisition unit 301, a learning unit 302, a determination image acquisition unit 303, and a determination unit 304.

[0086] The learning data acquisition unit 301 acquires learning data. The learning data is information for machine learning. The learning data is a set of a learning image and information indicating the position of an object in the learning image. As an example, in the objects in the learning image, there are included a specimen piece, a needle, and columnar portions provided on the specimen holder. Here, the types of objects in the learning image are the same as those of the objects in the determination image. For example, when the types of objects in the learning image are a specimen piece, a needle, or a columnar portion, the types of objects in the determination image are a specimen piece, a needle, or a columnar portion, respectively.

[0087] Here, in the present embodiment, as the learning image, a SIM image and an SEM image obtained in advance by irradiating an object with a charged particle beam are used. The charged particle beam is irradiated on the object from a specified direction. In the charged particle beam apparatus 10, since the direction of the lens barrel of the charged particle beam irradiation system is fixed, the direction of irradiating the charged particle beam on the object is determined in advance.

[0088] As an example, the information indicating the position of the object in the learning image is coordinates indicating the position of the object in the learning image. The coordinates indicating the position in the learning image are, for example, two-dimensional orthogonal coordinates, polar coordinates, etc.

[0089] The learning images include both the SIM image and the SEM image of the object. The learning images are the SIM image when observing the object from an inclined direction that is inclined by a predetermined angle from the vertical direction with respect to the specimen stage 12 and the SEM image when observing the object from the vertical direction of the specimen stage 12. That is, the learning images include the image when observing the object from the first direction based on the specimen stage 12 and the image when observing the object from the second direction. The second direction is a direction different from the first direction based on the specimen stage 12.

[0090] The learning unit 302 performs machine learning based on the learning data acquired by the learning data acquisition unit 301. The learning unit 302 stores the result of the learning as a machine learning model M in the storage unit 305. The learning unit 302 performs machine learning for each type of object in the learning images included in the learning data. Therefore, a machine learning model M is generated for each type of object in the learning images included in the learning data. The machine learning model M is an example of a machine learning model obtained by learning the first information of the first image including the first object.

[0091] In addition, in the following description, there are cases where the object photographed or depicted in the image is referred to as the object of the image.

[0092] Here, the machine learning performed by the learning unit 302 refers to, for example, deep learning using a convolutional neural network (CNN: Convolutional Neural Network). In this case, the machine learning model M refers to a multi-layer neural network in which the weights between the nodes are changed according to the correspondence between the learning image and the position of the object in the learning image. The multi-layer neural network includes an input layer having nodes corresponding to each pixel of the image and an output layer having nodes corresponding to each position in the image. When the brightness values of the pixels of the SIM and SEM images are input to the input layer, a group of values indicating the positions in the image is output from the output layer.

[0093] The determination image acquisition unit 303 acquires a determination image. The determination image is the SIM image and the SEM image output from the control computer 22. The determination image includes the image of the above-mentioned object. The object of the determination image includes the specimen piece Q, the used needle 18, etc., and objects related to the irradiation of the charged particle beam.

[0094] The determination image is both a SIM image when observing an object in an inclined direction after being inclined by a specified angle in the vertical direction with respect to the specimen stage 12 and an SEM image when observing the object in the vertical direction of the specimen stage 12. That is, the determination image includes an image when observing the object in the first direction and an image when observing the object in the second direction. Here, the first direction is a direction based on the specimen stage 12, and the second direction is a direction different from the first direction based on the specimen stage 12.

[0095] The determination unit 304 determines the position of the object included in the determination image acquired by the determination image acquisition unit 303 based on the machine learning model M obtained by the learning performed by the learning unit 302. Here, the position of the object included in the determination image includes, for example, the pick-up position of the specimen piece in the SIM image and the SEM image, the position of the tip of the needle in the SIM image and the SEM image, and the position of the columnar portion 44 in the SIM image and the SEM image. As an example, the determination unit 304 determines the coordinates of the object in the determination image as the position of the object included in the determination image.

[0096] In addition, the image processing computer 30 can also obtain a learned machine learning model from an external database, for example. In this case, the control unit 300 may not include the learning data acquisition unit 301 and the learning unit 302.

[0097] Hereinafter, regarding the operation of automatic micro-sampling (MS: Micro-sampling) performed by the control computer 22, that is, the operation of automatically transferring the specimen piece Q formed by processing the specimen S with a charged particle beam (convergent ion beam) to the specimen piece holder P, it will be roughly described in sequence as an initial setting process, a specimen piece pick-up process, and a specimen piece installation process.

[0098] (Initial setting process)

[0099] Figure 7 It is a diagram showing an example of the initial setting process of the present embodiment.

[0100] Step S10: The control computer 22 sets the mode and processing conditions. The setting of the mode refers to the setting of the presence or absence of the posture control mode described later according to the operator's input at the start of the automatic sequence. The setting of the processing conditions is the setting of the processing position, size, the number of specimen pieces Q, etc.

[0101] Step S20: The control computer 22 registers the position of the columnar portion 44. Here, the control computer 22 sends the SIM image and the SEM image including the columnar portion 44 as the object to the image processing computer 30.

[0102] In the present embodiment, the absorption current image data including the object is a set of the SIM image of the object and the SEM image of the object. That is, the SIM image and the SEM image including the object are a set of the SIM image when observing the object from an inclined direction inclined by a predetermined angle from the vertical direction with respect to the specimen stage 12 and the SEM image when observing the object from the vertical direction of the specimen stage 12.

[0103] The determination image acquisition unit 303 acquires a SIM image or an SEM image as a determination image from the image processing computer 30. The determination unit 304 determines the position of the columnar portion 44 included in the determination image acquired by the determination image acquisition unit 303 according to the machine learning model M. The determination unit 304 outputs the position information indicating the determined position of the columnar portion 44 to the control computer 22.

[0104] Here, the determination unit 304 determines the two-dimensional coordinates on the specimen stage 12 of the position of the object according to the SIM image when observing the object from an inclined direction inclined by a predetermined angle from the vertical direction with respect to the specimen stage 12. On the other hand, the determination unit 304 determines the two-dimensional coordinates of the position of the object on a plane perpendicular to the inclined direction according to the SEM image when observing the object from an inclined direction inclined by a predetermined angle from the vertical direction with respect to the specimen stage 12. The determination unit 304 determines the position of the object as a three-dimensional coordinate value according to the determined two-dimensional coordinates on the specimen stage 12 and the two-dimensional coordinates on the plane perpendicular to the inclined direction.

[0105] In addition, the determination unit 304 uses the direction in which the electron beam irradiation optical system 15 and the focused ion beam irradiation optical system 14 are arranged in the charged particle beam apparatus 10 and the direction information as the angle information between the two for the calculation of the three-dimensional coordinate value. The determination unit 304 stores the direction information in the storage unit 305 in advance, reads it out, or obtains the direction information from the control computer 22.

[0106] Here, in step S20, the object refers to the columnar portion 44. In the following processes, the process of the determination unit 304 determining the position of the object is the same.

[0107] Here, refer to Figures 8 to 12 , and the columnar portion 44 and the learning image of the columnar portion 44 for generating the machine learning model M will be described.

[0108] Figure 8 And Figure 9 is a diagram showing an example of the columnar portion 44 of the present embodiment. Figure 8 And Figure 9 The columnar portion A0 shown is an example of the design structure of the columnar portion 44. Here, Figure 8 is a top view of the columnar portion A0, Figure 9It is a side view of the columnar part A0. The columnar part A0 has a structure formed by bonding the pillar A01 to the bonding step structure of the base part A02.

[0109] Figure 10 It is a diagram showing an example of a learning image of the columnar part 44 of the present embodiment. The learning images X11, X12, and X13 are used for learning the position of the columnar part 44. In the learning images X11, X12, and X13, the information showing the position of the columnar part is shown as a circle.

[0110] In the learning images X11, X12, and X13, the shapes of the pillars A11, A21, and 31 are different from each other. On the other hand, in the learning images X11, X12, and X13, the shapes of the bases A12, A22, and A32 are the same.

[0111] In addition, as an example, the learning images X11, X12, and X13 are learning images for determining the position of the columnar part 44 included in the SIM image and the SEM image when observing the columnar part 44 from the horizontal direction of the specimen stage 12. In Figure 2 Although the focused ion beam irradiation optical system 14 and the electron beam irradiation optical system 15 do not face the specimen stage 12 from the horizontal direction of the specimen stage 12, either the focused ion beam irradiation optical system 14 or the electron beam irradiation optical system 15 may face the specimen stage 12 from the horizontal direction, and the learning images X11, X12, and X13 are learning images for determining the position of the columnar part 44 in this case.

[0112] Figure 11 It is a diagram showing an example of the columnar part 44 in which the pillar of the present embodiment does not form a step structure. Figure 11 The shown columnar part A4 is a side view of an example of the designed structure of the columnar part 44 in which the pillar does not form a step structure.

[0113] Figure 12 It is a diagram showing an example of a learning image of the columnar part 44 in which the pillar of the present embodiment does not form a step structure. As an example, the learning images X21, X22, and X23 are learning images for determining the position of the columnar part 44 included in the SEM image when observing the columnar part 44 from the vertical direction of the specimen stage 12.

[0114] In the learning images X21, X22, and X23, the shapes of the pillars A51, A61, and 71 are different from each other. On the other hand, in the learning images X21, X22, and X23, the shapes of the bases A52, A62, and A72 are the same.

[0115] In existing template matching, when the shapes of the supports are different, it is sometimes impossible to determine the position of the columnar portion. On the other hand, since the machine learning model M is generated by machine learning using learning images including the base portion of the columnar portion 44, in the machine learning model M, for example, the shape of the base portion is learned as a feature amount. Therefore, in the charged particle beam apparatus 10, even when the shapes of the supports are different, the determination accuracy of the columnar portion is improved.

[0116] Preferably, the object objects of the learning images include portions having the same shape among the object objects of the plurality of learning images.

[0117] Return Figure 7 Continue with the description of the initial setting process.

[0118] The control computer 22 registers the position of the columnar portion 44 based on the position information indicating the position of the columnar portion 44 determined by the image processing computer 30.

[0119] In addition, in the learning image of the columnar portion 44, it is preferable to include images of the columnar portions located at both ends of the specimen stage 43 in the columnar portion 44. The image processing computer 30 distinguishes and detects the columnar portions at both ends of the specimen stage 43 in the columnar portion 44 from the columnar portions other than the two ends based on the machine learning model M generated using the learning data including this learning image. The control computer 22 can also calculate the inclination of the specimen holder P based on the positions of the detected columnar portions at both ends. The control computer 22 can also correct the coordinate values of the position of the object based on the calculated inclination.

[0120] Step S30: The control computer 22 controls the focused ion beam irradiation optical system 14 to process the specimen S.

[0121] (Specimen piece picking process)

[0122] Figure 13 FIG. is an example showing a specimen piece picking process of the present embodiment. Here, picking means processing using a focused ion beam or separating and extracting a specimen piece Q from the specimen S using a needle.

[0123] Step S40: The control computer 22 adjusts the position of the specimen. Here, the control computer 22 moves the specimen stage 12 using the stage drive mechanism 13 so that the specimen piece Q as an object enters the field of view of the charged particle beam. Here, the control computer 22 uses the relative positional relationship between the reference mark Ref and the specimen piece Q. After moving the specimen stage 12, the control computer 22 performs position alignment of the specimen piece Q.

[0124] Step S50: The control computer 22 executes the movement of the needle 18.

[0125] Here, with reference to Figure 14 , the process for moving the needle 18 executed by the control computer 22 will be described. Figure 14 is a diagram showing an example of the movement process of the needle 18 of the present embodiment. Figure 14 Steps S510 to S540 of Figure 13 correspond to step S50 of

[0126] Step S510: The control computer 22 executes a needle movement (coarse adjustment) for moving the needle 18 using the needle driving mechanism 19.

[0127] Step S520: The control computer 22 detects the tip of the needle 18. Here, the control computer 22 sends absorption current image data including the needle 18 as an object to the image processing computer 30.

[0128] The determination image acquisition unit 303 acquires a SIM image and a SEM image as determination images from the image processing computer 30. The determination unit 304 determines the position of the needle 18 included in the determination images acquired by the determination image acquisition unit 303 as the position of the object according to the machine learning model M. The determination unit 304 outputs position information indicating the determined position of the needle 18 to the control computer 22.

[0129] Next, the control computer 22 executes a needle movement (fine adjustment) for moving the needle 18 using the needle driving mechanism 19 according to the position information indicating the position of the needle 18 determined by the image processing computer 30.

[0130] Here, with reference to Figures 15 to 18 , the needle 18 and the learning image of the needle 18 for generating the machine learning model M will be described.

[0131] Figure 15 is a diagram showing an example of SEM image data including the tip of the needle 18 of the present embodiment. Figure 16 is a diagram showing an example of SIM image data including the tip of the needle 18 of the present embodiment.

[0132] Figure 17 is a diagram showing an example of the tip of the needle 18 of the present embodiment. In Figure 17 as an example of the needle 18, the needle B1 is shown when observed from an inclined direction inclined by a predetermined angle with respect to the vertical direction of the specimen stage 12.

[0133] Figure 18This is a diagram showing an example of a learning image of the needle 18 according to this embodiment. The learning images Y31, Y32, and Y33 are used for learning the position of the tip of the needle 18. In the learning images Y31, Y32, and Y33, the information showing the position of the tip of the needle 18 is shown as a circle. In the learning images Y31, Y32, and Y33, the thicknesses of the tips of the needles are different from each other. On the other hand, in the learning images Y31, Y32, and Y33, the shapes of the tips of the needles are the same.

[0134] Regarding the thickness of the actual tip of the needle 18, the thickness changes due to cleaning. In the existing template matching, when the thicknesses of the tips of the needles are different, it is sometimes impossible to determine the position of the tip of the needle. On the other hand, since the machine learning model M is generated by machine learning using learning images including the tip of the needle 18, in the machine learning model M, for example, the shape of the tip of the needle 18 is learned as a feature amount. Therefore, in the charged particle beam device 10, even when the thicknesses of the tips of the needles are different, the determination accuracy of the tip of the needle is improved.

[0135] Return Figure 14 , and continue with the description of the movement process of the needle 18.

[0136] Step S530: The control computer 22 detects the pickup position of the specimen wafer Q. Here, the control computer 22 sends a SIM image and an SEM image including the specimen wafer Q as an object to the image processing computer 30.

[0137] Here, with reference to Figure 19 and Figure 20 , the specimen wafer Q and the learning image of the specimen wafer Q used for generating the machine learning model M will be described.

[0138] Figure 19 This is a diagram showing an example of SIM image data including the specimen wafer Q of this embodiment. In Figure 19 , as an example of the specimen wafer Q, the specimen wafer Q71 and the circle showing the pickup position are shown together.

[0139] Figure 20This is a diagram showing an example of a learning image of the sample piece Q of the present embodiment. The learning images Z11, Z12, and Z13 are used for learning the position of the front end of the sample piece Q. In the learning images Z11, Z12, and Z13, the information on the pickup position of the sample piece Q is shown as a circle. In the learning images Z11, Z12, and Z13, the sizes and surface shapes of the sample pieces are different from each other. On the other hand, in the learning images Z11, Z12, and Z13, the shapes of the sample pieces at the pickup positions are the same.

[0140] The surface shape of the actual sample piece is different for each individual. In the existing template matching, when the surface shapes of the sample pieces are different, it is sometimes impossible to determine the pickup position of the sample piece. In addition, in the existing template matching, when the contrast and focus are different between the image of the sample piece and the template, the template matching sometimes fails and it is impossible to determine the pickup position of the sample piece.

[0141] On the other hand, since the machine learning model M is generated based on machine learning using the learning images including the pickup positions of the sample piece Q, in the machine learning model M, for example, the shape of the pickup position of the sample piece Q is learned as a feature amount. Therefore, in the charged particle beam apparatus 10, even when the surface shapes of the sample pieces are different, the determination accuracy of the pickup position of the sample piece Q is improved.

[0142] Return Figure 14 , and continue with the description of the movement process of the needle 18.

[0143] Step S540: The control computer 22 moves the needle 18 to the detected pickup position.

[0144] Above, the control computer 22 ends the movement process of the needle 18.

[0145] Return Figure 13 , and continue with the description of the sample piece pickup process.

[0146] Step S60: The control computer 22 connects the needle 18 to the sample piece Q. Here, the control computer 22 uses a deposited film for the connection.

[0147] Step S70: The control computer 22 processes and separates the sample S and the sample piece Q. Here, Figure 21 The case of the processing separation is shown. This is a diagram showing the cutting position T1 of the support portion Qa of the sample S and the sample piece Q in the SIM image data of the embodiment of the present invention.

[0148] In addition, in the present embodiment, for the prefabricated and processed specimen piece Q0, a specimen piece picking process and a specimen piece mounting process are also performed separately. In this case, the picking position of the specimen piece Q0 can also be specified and input to the control computer 22, so that after the position adjustment of the specimen piece transfer unit (the needle 18) and the specimen piece Q0, the cutting position T1 is determined by machine learning. Figure 21 In the machine learning in this case, as the first image, an image is used which shows the position (cutting position) where the specimen piece transfer unit approaches the specimen piece in the specimen extraction process of extracting the specimen piece.

[0149] In this case, even if the processing dimension and shape information showing the processing dimensions and shape of the specimen piece Q0 is not input to the control computer 22, the extraction and separation of the specimen piece Q0 can be performed. In addition, after extracting the specimen piece Q0, the subsequent specimen piece mounting process can be performed in the same manner.

[0150] Step S80: The control computer 22 retracts the needle 18. Here, the control computer 22 detects the position of the tip of the needle 18 in the same manner as the movement process of the needle 18 in step S50, and moves the needle 18 to retract it.

[0151] Step S90: The control computer 22 moves the specimen stage 12. Here, the control computer 22 uses the stage drive mechanism 13 to move the specimen stage 12 so that the specific columnar portion 44 registered in the above step S20 enters the observation field region of the charged particle beam.

[0152] (Specimen piece mounting process)

[0153] Figure 22 is a diagram showing an example of the specimen piece mounting process of the present embodiment. Here, the specimen piece mounting process refers to the process of transferring the extracted specimen piece Q to the specimen piece holder P.

[0154] Step S100: The control computer 22 determines the transfer position of the specimen piece Q. Here, the control computer 22 determines the specific columnar portion 44 registered in the above step S20 as the transfer position.

[0155] Step S110: The control computer 22 detects the position of the needle 18. Here, the control computer 22 detects the position of the tip of the needle 18 in the same manner as in the above step S520.

[0156] Step S120: The control computer 22 moves the needle 18. Here, the control computer 22 uses the needle driving mechanism 19 to move the needle 18 to the transfer position of the specimen piece Q determined in step S100. The control computer 22 stops the needle 18 with a predetermined gap between the columnar portion 44 and the specimen piece Q.

[0157] Step S130: The control computer 22 connects the specimen piece Q connected to the needle 18 to the columnar portion 44.

[0158] Step S140: The control computer 22 separates the needle 18 from the specimen piece Q. Here, the control computer 22 separates by cutting the deposition film DM2 connecting the needle 18 and the specimen piece Q.

[0159] Step S150: The control computer 22 retracts the needle 18. Here, the control computer 22 uses the needle driving mechanism 19 to move the needle 18 away from the specimen piece Q by a predetermined distance.

[0160] Step S160: The control computer 22 determines whether to perform the next sampling. Here, performing the next sampling means continuing sampling from different positions of the same specimen S. Since the number of samples to be taken is set in advance in step S10, the control computer 22 confirms this data and then determines whether to perform the next sampling. If it is determined to perform the next sampling, the control computer 22 returns to step S50 and continues the subsequent steps as described above to perform the sampling operation. On the other hand, if the control computer 22 determines not to perform the next sampling, the series of processes of the automatic MS is ended.

[0161] In addition, in the present embodiment, an example in which the learning data is a group of a learning image and information indicating the position of an object in the learning image is described, but it is not limited thereto. The learning data may include various types of specimens, scanning parameters (such as the acceleration voltage of the focused ion beam irradiation optical system 14 and the electron beam irradiation optical system 15), information indicating the number of uses after cleaning the needle 18, and parameter information such as whether foreign matter adheres to the tip of the needle 18, in addition to the learning image.

[0162] In this case, the machine learning model M1 is generated by performing machine learning based on the learning image and the parameter information. In addition, the determination unit 304 obtains not only the image data of the SIM image and the SEM image from the control computer 22, but also the parameter information, and determines the position of the object in the image based on the image data, the parameter information, and the machine learning model M1.

[0163] In addition, the parameter information may further include the above-described direction information. When the direction information is included in the learning data, the machine learning model M1 is generated by learning the relationship between the object to be learned and the direction of observing the object (the direction based on the specimen stage 12). Therefore, the determination unit 304 does not need to use the direction information in the determination of the position of the object.

[0164] In addition, as described above, the computer (the control computer 22 in the present embodiment) determines the result of the position related to the second object (the columnar portion 44, the needle 18, and the specimen piece Q in the present embodiment) based on the machine learning-based model (the machine learning model M1 in the present embodiment) of the image processing computer 30 and the second information including the second image (the SIM image and the SEM image of the columnar portion 44, the needle 18, and the specimen piece Q in the present embodiment), and controls the position related to the second object (the columnar portion 44, the needle 18, and the specimen piece Q in the present embodiment). In addition, the image processing computer 30 and the control computer 22 may be integrally provided in the charged particle beam apparatus 10.

[0165] (Second Embodiment)

[0166] Hereinafter, the second embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0167] In the present embodiment, a case where a simulation image generated according to the type of the object is used as a learning image, or a machine learning model to be used is selected according to the type of the object will be described.

[0168] The charged particle beam apparatus 10 of the present embodiment is referred to as a charged particle beam apparatus 10a, and the image processing computer 30 is referred to as an image processing computer 30a.

[0169] Figure 23 FIG. is an example showing the structure of the image processing computer 30a of the present embodiment. Comparing the image processing computer 30a of the present embodiment ( Figure 23 ) and the image processing computer 30 of the first embodiment ( Figure 6 ), the learning image generation unit 306a, the classification unit 307a, the machine learning model M1a, and the classification learning model M2a are different. Here, the functions of other components are the same as those in the first embodiment. The description of the functions the same as those in the first embodiment is omitted, and in the second embodiment, the description will be centered on the parts different from the first embodiment.

[0170] The control unit 300a further includes a learning image generation unit 306a and a classification unit 307a in addition to the learning data acquisition unit 301, the learning unit 302, the determination image acquisition unit 303, and the determination unit 304.

[0171] The learning image generation unit 306a generates a simulation image PI as a learning image. In the present embodiment, the simulation image PI refers to an image generated based on a SIM image and an SEM image obtained in advance by irradiating an object with a charged particle beam. As an example, the learning image generation unit 306a generates the simulation image PI based on the bare workpiece BW and the pattern image PT.

[0172] The bare workpiece BW refers to an image that shows the shape of the object by removing the surface pattern from the object. The bare workpiece BW is preferably a plurality of images showing the shapes of a plurality of objects with different sizes, contrasts, foci, etc. The bare workpiece BW is different from the SIM image and the SEM image and is an image drawn using image software.

[0173] The pattern image PT is an image indicating a pattern corresponding to the internal structure of the object. The pattern image PT can be a SIM image and an SEM image obtained by irradiating with a charged particle beam, or an image drawn using image software.

[0174] The learning image generation unit 306a uses a simulation image generation algorithm to apply random noise to the pattern corresponding to the internal structure of the object shown in the pattern image PT and superimposes it on the bare workpiece BW to generate the simulation image PI.

[0175] In the present embodiment, as an example, a case where the learning image generation unit 306a generates the simulation image PI as a learning image of the specimen piece Q is described, but it is not limited thereto. The learning image generation unit 306a can also generate the simulation image PI as a learning image of the needle 18 and the columnar portion 44.

[0176] In addition, the learning image generation unit 306a can also include the SIM image and the SEM image obtained in advance by irradiating the object of the first embodiment with a charged particle beam in the learning image. That is, the learning image generation unit 306a can use only the simulation image PI as the learning image, or can use the simulation image PI in combination with the SIM image or the SEM image.

[0177] In machine learning, the learning unit 302 extracts the surface shape of the object and the pattern of the internal structure from the learning image generated by the learning image generation unit 306a as feature amounts, and generates a machine learning model M1a.

[0178] Here, with reference to Figures 24 to 26 , a method for generating the simulation image PI will be described.

[0179] Figure 24 is a diagram showing an example of the bare workpiece BW of the present embodiment. In Figure 24In [description], as the bare workpieces BW of the specimen piece Q, the bare workpieces BW1, BW2, and BW3 are shown. The bare workpieces BW1, BW2, and BW3 are images imitating the shapes of specimen pieces Q of multiple sizes. In addition, the bare workpieces BW1, BW2, and BW3 respectively contain images corresponding to the needles 18 as information showing the picking positions.

[0180] Figure 25 is a diagram showing an example of the pattern image PT of the present embodiment. In Figure 25 In it, as the pattern image PT, the user sample U1 is shown. The user sample U1 is an image prepared in advance according to the type of the specimen piece Q to be processed by the user of the charged particle beam device 10a. In the user sample U1, for the specimen piece composed of multiple layers, patterns corresponding to the types of substances constituting these multiple layers are depicted.

[0181] Figure 26 is a diagram showing an example of the simulation image PI of the present embodiment. In Figure 26 In it, as the simulation image PI, those based on Figure 24 the bare workpieces BW1, BW2, and BW3 and Figure 25 the user sample U1 of [description] are shown as the simulation images PI1, PI2, and PI3. The simulation images PI1, PI2, and PI3 superimpose the patterns of the internal structure shown in the user sample U1 on the shapes of specimen pieces Q of multiple sizes.

[0182] Return Figure 23 , and continue with the description of the structure of the image processing computer 30a.

[0183] The classification unit 307a classifies the determination image acquired by the determination image acquisition unit 303 according to the classification learning model M2a. Here, the classification unit 307a does not necessarily classify the determination image. Whether the classification unit 307a classifies the determination image is set in the image processing computer 30 according to the setting input to the control computer 22, for example.

[0184] The classification learning model M2a is a model for selecting, from among the multiple models included in the machine learning model M1a, the model used by the determination unit 304 for determination according to the type of the object. Here, the multiple models included in the machine learning model M1a are distinguished not only according to the learning data set used for the generation of the model but also according to the machine learning algorithm.

[0185] For example, the classification learning model M2a, for example, associates the type of the specimen piece Q processed by each user with the models included in the machine learning model M1a. The classification learning model M2a is pre-generated by machine learning and stored in the storage unit 305.

[0186] Next, with reference to Figure 27 , the process of detecting the pick-up position of the test specimen wafer Q will be described as an operation of the automatic MS of the charged particle beam apparatus 10a using the classification learning model M2a.

[0187] Figure 27 It is a diagram showing an example of the detection process of the pick-up position of the present embodiment.

[0188] Step S310: The classification unit 307a classifies the determination image acquired by the determination image acquisition unit 303 according to the classification learning model M2a.

[0189] Step S320: The classification unit 307a selects, based on the classification result, the machine learning model to be used by the determination unit 304 in the determination from among the plurality of models included in the machine learning model M1a.

[0190] Step S330: The determination unit 304 determines the position of the object included in the determination image acquired by the determination image acquisition unit 303 according to the machine learning model selected by the classification unit 307a.

[0191] In addition, in the above-described embodiment, an example of the case where the charged particle beam apparatuses 10 and 10a include two charged particle beam irradiation optical systems, i.e., the convergent ion beam irradiation optical system 14 and the electron beam irradiation optical system 15, has been described, but it is not limited thereto. The charged particle beam apparatus may also include one charged particle beam irradiation optical system. In this case, preferably, in the determination image obtained by irradiating with the charged particle beam through the charged particle beam irradiation optical system, for example, in addition to showing the object, the shadow of the object is also shown. Further, in this case, the object is the needle 18.

[0192] The shadow of the needle 18 refers to a phenomenon that occurs when the needle 18 approaches the surface of the specimen wafer Q and blocks the secondary electrons (or secondary ions) generated from the surface of the specimen wafer Q near the needle 18 from reaching the detector 16 when observed from an inclined direction inclined by a predetermined angle from the vertical direction with respect to the specimen stage 12. The closer the distance between the needle 18 and the surface of the specimen wafer Q, the more obvious this phenomenon becomes. Therefore, the closer the distance between the needle 18 and the surface of the specimen wafer Q, the higher the brightness value of the shadow in the determination image.

[0193] In addition to determining the position of the tip of the needle 18 in the determination image as two-dimensional coordinates, the image processing computer 30 also calculates the distance between the tip of the needle 18 and the surface of the specimen wafer Q based on the brightness value of the shadow of the needle 18. Thus, the image processing computer 30 determines the position of the tip of the needle 18 as three-dimensional coordinate values according to the determination image.

[0194] In addition, in the above-described embodiment, it may also be that the control computer 22 generates absorption current image data with the scanning speed set to a second speed slower than the first speed, and the image processing computer 30 sets the resolution of the image included in the absorption current image data generated with the scanning speed set to the second speed to a second resolution higher than the first resolution, and then determines the position of the object according to the machine learning model M.

[0195] Here, the scanning speed refers to the speed at which the irradiation position of the charged particle beam is scanned during the process of the control computer 22 generating absorption current image data. The first speed refers to, for example, the speed at which the irradiation position of the charged particle beam is scanned by an existing charged particle beam device. The second speed is an arbitrary speed slower than the first speed. The second speed is, for example, the scanning speed selected in an existing charged particle beam device to obtain a high-definition image for improving the success rate of template matching.

[0196] The resolution refers to the density of the pixels constituting the image. The first resolution refers to, for example, the resolution of the SIM image and the SEM image included in the absorption current image data generated in an existing charged particle beam device. The second resolution is an arbitrary resolution having a higher spatial frequency than the first resolution.

[0197] In the following description, "setting the scanning speed to the second speed" is also referred to as "setting the scanning speed to a low speed" for example. In addition, "converting the resolution of the image from the first resolution to the second resolution" is also referred to as "super-resolving the image" for example.

[0198] Here, the processing of the image processing computer 30 in the following case is described. The case is that the control computer 22 generates absorption current image data with the scanning speed set to a low speed, super-resolves the resolution of the SIM image and the SEM image included in the absorption current image data generated by the image processing computer 30 with the scanning speed set to a low speed, and then determines the position of the object according to the machine learning model M. This processing is performed in the above Figure 7 shown step S20, Figure 14 shown step S520, Figure 22 shown step S110, etc.

[0199] The determination image acquisition unit 303 acquires a SIM image and an SEM image as determination images from the image processing computer 30. These SIM image and SEM image are images included in the absorption current image data generated by setting the scanning speed to a low speed by the control computer 22. The determination unit 304 performs a process of super-resolving the determination images acquired by the determination image acquisition unit 303. For the super-resolution technique used by the determination unit 304 in super-resolution, any super-resolution technique can be used without limitation. The determination unit 304, for example, converts the resolution of the SIM image and the SEM image from the first resolution to the second resolution. Here, the determination unit 304 not only converts the resolution of the SIM image and the SEM image, but also performs a process of making the spatial frequency of the image of the object included in the SIM image and the SEM image higher than the spatial frequency of the image before conversion.

[0200] The determination unit 304 determines the position of the object included in the super-resolved determination image according to the machine learning model M. The determination unit 304 outputs the position information indicating the determined position of the object to the control computer 22.

[0201] As described above, when the control computer 22 generates absorption current image data by setting the scanning speed to a second speed slower than the first speed, and the image processing computer 30 sets the resolution of the image included in the absorption current image data generated by setting the scanning speed to the second speed to a second resolution higher than the first resolution, and then determines the position of the object according to the machine learning model M, when the scanning speed is set to the second speed, compared with the case where the resolution of the image is not set to the second resolution, the processing time for determining the position of the object can be shortened, and the determination accuracy can be improved.

[0202] In addition, the control computer 22 can also super-resolve the absorption current image data acquired by setting the scanning speed to the second speed, and then determine the position of the object according to the machine learning model M. As a result, when the position of the object cannot be determined, the absorption current image data is acquired by setting the scanning speed to the first speed, and thus the position of the object is determined according to the machine learning model M without super-resolution. If the reason for the inability to determine the position of the object is insufficient super-resolution, by performing a retry process using the absorption current image data acquired by setting the scanning speed to the first speed, it may be possible to correctly detect the position of the object.

[0203] In addition, a part of the control computer 22, the image processing computers 30 and 30a in the above-described embodiments, such as the learning data acquisition unit 301, the learning unit 302, the determination image acquisition unit 303, the determination unit 304, the learning image generation unit 306a, and the classification unit 307a, can also be implemented by a computer. In this case, it can also be implemented by recording a program for implementing this control function in a computer-readable recording medium, and causing a computer system to read and execute the program recorded in this recording medium. In addition, the "computer system" mentioned here is the computer system built in the control computer 22, the image processing computers 30 and 30a, and includes hardware such as an OS and peripheral devices. In addition, the "computer-readable recording medium" refers to removable media such as a floppy disk, an optical disk, a ROM, a CD-ROM, and a storage device such as a hard disk built in a computer system. Furthermore, the "computer-readable recording medium" can also include a structure that dynamically holds a program for a short time, such as a communication line in the case of transmitting a program via a network such as the Internet or a communication line such as a telephone line, and a structure that holds a program for a certain time, such as a volatile memory inside a computer system serving as a server or a client in this case. In addition, the above program can be a program for implementing a part of the above functions, and can also be a program that can implement the above functions by combining with a program already recorded in a computer system.

[0204] In addition, a part or all of the control computer 22, the image processing computers 30 and 30a in the above-described embodiments can be implemented as an integrated circuit such as an LSI (Large Scale Integration). Each functional block of the control computer 22, the image processing computers 30 and 30a can be separately processorized, or a part or all of them can be integrated and processorized. In addition, the method of integrating into an integrated circuit is not limited to LSI, and can also be implemented using an application-specific circuit or a general-purpose processor. In addition, in the case where an integrated circuit technology replacing LSI appears due to the progress of semiconductor technology, an integrated circuit based on this technology can also be used.

[0205] As described above, one embodiment of the present invention has been described in detail with reference to the accompanying drawings. However, the specific structure is not limited to the above-described embodiment, and various design changes and the like can be made without departing from the gist of the present invention.

Claims

1. A charged particle beam device that automatically produces a specimen piece from a specimen, the charged particle beam device comprising: A charged particle beam irradiation optical system that irradiates a charged particle beam; A specimen stage that moves while carrying the specimen; A specimen piece transfer unit that holds and transports the specimen piece separated and removed from the specimen; A holder fixing stage that holds a specimen piece holder for transferring the specimen piece; and A computer that controls the position related to the second object based on a machine learning model obtained from learning the first information and the second information, wherein, The first information includes a first image of a first object, and the second information includes a second image obtained by irradiating with the charged particle beam, The first object and the second object are objects related to the irradiation of the charged particle beam, The second object includes the specimen piece, The first image includes an image showing the shape of the specimen piece before the specimen piece is separated and removed.

2. The charged particle beam device according to claim 1, wherein, The second object includes a part of the specimen stage included in the specimen piece holder.

3. The charged particle beam device according to claim 1, wherein, The second object includes a needle used in the specimen piece transfer unit.

4. The charged particle beam device according to any one of claims 1 to 3, wherein, The first image is an image showing the position where the specimen piece transfer unit approaches the specimen piece in the specimen removal process of removing the specimen piece.

5. The charged particle beam device according to any one of claims 1 to 3, wherein, The first image is an image showing the position where the specimen piece is separated and removed from the specimen.

6. The charged particle beam device according to any one of claims 1 to 3, wherein, The first image is a simulation image generated according to the type of the second object.

7. The charged particle beam device according to any one of claims 1 to 3, wherein, The type of the first object is the same as the type of the second object.

Images