TWI874449B - Charged particle beam device - Google Patents

Abstract

[Topic] Capable of speeding up automatic micro-sampling.   [Solution] A charged particle beam device that automatically prepares a sample sheet from a sample, the charged particle beam device comprising: a charged particle beam irradiation optical system that irradiates a charged particle beam; a sample stage that carries and moves the sample; a sample sheet transfer unit that holds and transports the sample sheet separated and extracted from the sample; a holder fixing table that holds a sample sheet holder that transfers the sample sheet; and a computer that controls a position related to a second object based on a mechanical learning model that learns first information including a first image of a first object and second information including a second image obtained by irradiation with the charged particle beam.

Description

Charged particle beam device

The present invention relates to a charged particle beam device.

Conventionally, there is known a device for extracting a sample piece produced by irradiating a sample with a charged particle beam composed of electrons or ions, and processing the sample piece into a shape suitable for various processes such as observation, analysis, and measurement using a transmission electron microscope (TEM) or the like (Patent Document 1). In the device described in Patent Document 1, so-called micro-sampling (MS) is performed, that is, when observing using a transmission electron microscope, a tiny thin film sample piece is taken out from a sample as an observation object, and the thin film sample piece is fixed on a sample holder to produce a TEM sample.

It is known that in the preparation of thin-sheet samples for TEM observation, a charged particle beam device detects objects such as the tip of a microprobe, the pickup position of a thin-sheet sample, and the end of a support on a mesh holder by template matching (Patent Document 2). In the charged particle beam device described in Patent Document 2, position control related to the object is performed based on a template prepared based on an image of the object obtained by irradiation with a charged particle beam and position information obtained from the image of the object. As a result, in the charged particle beam device described in Patent Document 2, MS can be automatically executed (automatic MS). [Prior Art Document] [Patent Document]

Patent document 1: Japanese Patent Publication No. 2019-102138 Patent document 2: Japanese Patent Publication No. 2016-157671

[The problem the invention is trying to solve]

In the charged particle beam device described in Patent Document 2, a sample image must be acquired every time the position of the object is controlled, and the speed of the automatic MS is reduced by the amount of time required to acquire the image. For example, the shape of the tip of the microprobe changes due to cleaning or sample adhesion, so a sample image must be acquired every time the position of the object is controlled. In addition, the sample image of the pickup position of the thin sample also decreases in matching accuracy due to differences in contrast, focus, etc., so a sample image must be acquired before starting position control. In addition, since there are individual differences in the support angle, the user registers the position of the support on the image by mouse operation every time. On the other hand, in the charged particle beam device described in Patent Document 2, in order to improve the success rate of template matching, the scanning speed must be reduced to acquire a high-precision image. Thus, in the past, the speed of automatic MS was insufficient, and there was a demand to increase the speed of automatic MS and the amount of transportation.

The present invention is made in view of the above-mentioned problems, and provides a charged particle beam device capable of increasing the speed of automatic MS. [Technical means for solving the problem]

In order to solve the above-mentioned problems and achieve the purpose, the present invention adopts the following method. (1) One aspect of the present invention is a charged particle beam device that automatically produces a sample sheet from a sample, the charged particle beam device comprising: a charged particle beam irradiation optical system for irradiating a charged particle beam; a sample stage for carrying and moving the sample; a sample sheet transfer unit for holding and transporting the sample sheet separated and removed from the sample; a holder fixing table for holding and transferring the sample sheet; and a computer for controlling the position related to the second object based on a mechanical learning model that learns first information including a first image of a first object and second information including a second image obtained by irradiating the charged particle beam.

In the composite charged particle beam device of the embodiment described in (1) above, the position of the object can be detected based on mechanical learning, so the automatic MS can be accelerated. In the charged particle beam device 10, since the position of the object is detected based on mechanical 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 the automatic MS and improving the transmission volume. In the past, in order to improve the success rate of template matching in charged particle beam devices, the scanning speed was reduced to obtain a high-precision image, but in mechanical learning, position detection can be performed even if the image is not high-precision, so the scanning speed when obtaining the image can be increased, the automatic MS can be accelerated, and the transmission volume can be improved. In a charged particle beam device, the work that was previously performed manually by the user when preparing a processing recipe can be automated, thereby simplifying recipe preparation. In addition, in a charged particle beam device, it is not necessary to prepare a recipe for each sample, so it becomes a system structure that can resist shape changes.

(2) In the charged particle beam device described in (1), the second object includes a portion of a sample table provided in the sample sheet holder. In the composite charged particle beam device of the embodiment described in (2), since the position of the portion of the sample table can be detected based on machine learning, the process of connecting the sample sheet to the portion of the sample table can be accelerated in the automatic MS.

(3) In the charged particle beam device described in (1) or (2), the second object includes a needle used for the sample sheet transfer unit. In the composite charged particle beam device described in (3), the position of the tip of the needle can be detected based on mechanical learning, so that the process of moving the needle can be accelerated in the automatic MS.

(4) In the charged particle beam device described in any one of (1) to (3), the second object includes the sample sheet, and the first image is an image showing a position where the sample sheet transfer unit is brought close to the sample sheet in a sample extraction process for removing the sample sheet. In the composite charged particle beam device described in the embodiment of (4), the position where the sample sheet transfer unit is brought close to the sample sheet can be detected in the sample extraction process for removing the sample sheet based on mechanical learning, so that in the automatic MS, the process of bringing the needle close to the sample sheet can be accelerated.

(5) In the charged particle beam device described in any one of (1) to (4) above, the second object includes the sample sheet, and the first image is an image showing the position where the sample sheet is separated from the sample and removed. In the composite charged particle beam device described in the embodiment of (5) above, the position where the sample sheet is separated from the sample and removed can be detected based on mechanical learning, so that in the automatic MS, the process of connecting the sample sheet to the needle can be accelerated.

(6) In the charged particle beam device described in any one of (1) to (5), the first image is a simulated image generated in accordance with the type of the second object. In the composite charged particle beam device described in the embodiment described in (6), even when it is not possible to prepare a sufficient number of images obtained by irradiation with an actual charged particle beam as the first image, simulated images can be used in place of these images, thereby improving the accuracy of machine learning for learning the first information.

(7) In the charged particle beam device described in any one of (1) to (6), the type of the first object is the same as the type of the second object. In the composite charged particle beam device described in the embodiment of (7), the position of the object can be detected based on mechanical learning of the first information of the first image of the first object of the same type as the second object, so that the mechanical learning can be improved compared to the case where the types of the first object and the second object are different. [Effect of the invention]

According to the present invention, automatic micro-sampling can be accelerated.

(First implementation form)

Hereinafter, the embodiment of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing an example of the structure of a charged particle beam device 10 and an image processing computer 30 of the present embodiment. The control computer 22 of the charged particle beam device 10 acquires image data acquired by irradiation of the charged particle beam. Data is sent/received between the control computer 22 and the image processing computer 30. The image processing computer 30 determines the object contained in the image data received from the control computer 22 based on the mechanical 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. The control computer 22 is an example of a computer that controls the position related to the second object based on a mechanical learning model that learns the first information of the first image including the first object and the second information including the second image obtained by irradiation with the charged particle beam. In addition, the image processing computer 30 may also be provided in the charged particle beam device 10.

Here, the structure of the charged particle beam device 10 is described with reference to FIG. 2. (Charged particle beam device) FIG. 2 is a diagram showing an example of the structure of the charged particle beam device 10 of the embodiment. The charged particle beam device 10 includes a sample chamber 11, a sample table 12, a table driving 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 driving mechanism 19, an absorption current detector 20, a display device 21, a control computer 22, and an input device 23.

The sample chamber 11 maintains the interior in a vacuum state. The sample stage 12 fixes the sample S and the sample sheet holder P inside the sample chamber 11. Here, the sample stage 12 has a holder fixing table 12a for holding the sample sheet holder P. The holder fixing table 12a may be a structure capable of mounting a plurality of sample sheet holders P.

The stage drive mechanism 13 drives the sample stage 12. Here, the stage drive mechanism 13 is housed inside the sample chamber 11 in a state connected to the sample stage 12, and displaces the sample stage 12 relative to a predetermined axis in response to a control signal output from the control computer 22. The stage drive mechanism 13 has a moving mechanism 13a that moves the sample stage 12 in parallel at least along the X-axis and the Y-axis, and the Z-axis in the vertical direction orthogonal to the X-axis and the Y-axis, and the aforementioned X-axis and the Y-axis are parallel to the horizontal plane and orthogonal to each other. The stage driving mechanism 13 includes a tilting mechanism 13b for tilting the sample stage 12 around the X-axis or the Y-axis, and a rotating mechanism 13c for rotating the sample stage 12 around the Z-axis.

The focused ion beam irradiation optical system 14 irradiates the focused ion beam (FIB) to the irradiation target within the specified irradiation area (i.e., scanning range) inside the sample chamber 11. Here, the focused ion beam irradiation optical system 14 irradiates the focused ion beam to the irradiation target such as the sample S and the sample sheet Q placed on the sample stage 12 and the needle 18 existing in the irradiation area from the vertical upper side to the lower side.

The focused ion beam irradiation optical system 14 includes an ion source 14a for generating ions and an ion optical system 14b for focusing and deflecting ions extracted from the ion source 14a. The ion source 14a and the ion optical system 14b are controlled in response to a control signal output from a control computer 22, and the control computer 22 controls the irradiation position and irradiation conditions of the focused ion beam.

The electron beam irradiation optical system 15 irradiates an electron beam (EB) to an irradiation target within a predetermined irradiation area within the sample chamber 11. Here, the electron beam irradiation optical system 15 can irradiate an electron beam to an irradiation target such as a sample S fixed on the sample stage 12, a sample sheet Q, and a needle 18 existing in the irradiation area from the upper side to the lower side in an inclined direction inclined at a predetermined angle (e.g., 60°) relative to the vertical direction of the lead.

The electron beam irradiation optical system 15 includes an electron source 15a for generating electrons and an electron optical system 15b for focusing and deflecting the electrons emitted from the electron source 15a. The electron source 15a and the electron optical system 15b are controlled in response to a control signal output from a control computer 22, and the control computer 22 controls the irradiation position and irradiation conditions of the electron beam.

In addition, the configurations of the electron beam irradiation optical system 15 and the focused ion beam irradiation optical system 14 may be reversed, with the electron beam irradiation optical system 15 being configured in the lead vertical direction and the focused ion beam irradiation optical system 14 being configured in an inclined direction at a predetermined angle relative to the lead vertical direction.

The detector 16 is used to detect secondary charged particles (secondary electrons, secondary ions) R, which are generated from the irradiated object by irradiation with a focused ion beam or an electron beam. The gas supply unit 17 supplies gas G to the surface of the irradiated object. The needle 18 takes out a tiny sample piece Q from the sample S fixed on the sample table 12, holds the sample piece Q and moves it to the sample piece holder P. The needle driving mechanism 19 drives the needle 18 to transport the sample piece Q. In the following content, the needle 18 and the needle driving mechanism 19 are sometimes collectively referred to as a sample piece transfer unit.

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

The control computer 22 controls at least the table 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 sample room 11, and is connected to a display device 21 and an input device 23 such as a mouse and a keyboard that outputs a signal corresponding to an input operation of the operator. The control computer 22 centrally controls the operation of the charged particle beam device 10 using a signal output from the input device 23 or a signal generated by a preset automatic operation control process.

Here, as described above, the control computer 22 controls the position of the object based on the determination result of the image processing computer 30. The control computer 22 has a communication interface for communicating with the image processing computer 30.

In addition, the control computer 22 images the inflow current signal output from the absorption current detector 20 as absorption current image data. Here, the control computer 22 converts the detection amount of the secondary charged particles R detected by the detector 16 into a brightness signal corresponding to the irradiation position while scanning the irradiation position of the charged particle beam, and generates absorption current image data showing the shape of the irradiated object based on the two-dimensional position distribution of the detection amount of the secondary charged particles R. In the absorption current image mode, the control computer 22 scans the irradiation position of the charged particle beam while detecting the absorption current flowing through the needle 18, thereby generating absorption current image data showing the shape of the needle 18 based on the two-dimensional position distribution of the absorption current (absorption current image). The control computer 22 displays the generated image data on the display device 21. The display device 21 displays image data and the like based on the secondary charged particles R detected by the detector 16 .

The charged particle beam device 10 irradiates the surface of an irradiation target with a focused ion beam while scanning, thereby enabling imaging of the irradiation target, various processes (excavation, trimming, etc.) by sputtering, deposition film formation, and the like.

FIG3 is a top view showing a sample piece Q before being removed from the sample S, which is formed by irradiating the surface (shaded part) of the sample S with a focused ion beam in the charged particle beam device 10 of the embodiment of the present invention. Symbol F represents the processing frame of the focused ion beam, that is, the scanning range of the focused ion beam, and shows the processing area H excavated by sputtering processing on the inner side (white part) thereof by irradiation with the focused ion beam. Reference mark Ref is a reference point showing the position where the sample piece Q is formed (left without excavation). A deposited film is used to know the approximate position of the sample piece Q, and a micro-hole is used to perform precise position alignment. In the sample S, the sample piece Q is etched in the following manner so that the support portion Qa connected to the sample S is left and the peripheral portions of the side and bottom sides are cut and removed, and the sample piece Q is cantilevered and supported on the sample S by the support portion Qa.

Next, the sample holder P is described with reference to FIG. 4 and FIG. 5 . FIG. 4 is a top view of the sample holder P, and FIG. 5 is a side view. The sample holder P comprises: a base 42 having a substantially semicircular plate shape with a cutout portion 41, and a sample table 43 fixed to the cutout portion 41. As an example, the base 42 is formed of a circular plate-shaped metal. The sample table 43 is in the shape of a comb and has a plurality of columnar portions (hereinafter also referred to as pillars) 44 for transferring the sample Q, which are separately arranged and protruding.

(Image processing computer) Next, the image processing computer 30 is described with reference to FIG. 6 . FIG. 6 is a diagram showing an example of the structure of the image processing computer 30 of the present embodiment. The image processing computer 30 includes a control unit 300 and a memory unit 305 . The control unit 300 includes a learning data acquisition unit 301 , a learning unit 302 , a judgment image acquisition unit 303 , and a judgment unit 304 .

The learning data acquisition unit 301 acquires learning data. The learning data is learning information used for mechanical learning. The learning data is a combination of a learning image and information showing the position of an object in the learning image. As an example, the objects in the learning image include a sample sheet, a needle, and a columnar portion provided in a sample sheet holder. Here, the type of the object in the learning image is the same as the type of the object in the judgment image. For example, when the type of the object in the learning image is a sample sheet, a needle, or a columnar portion, the type of the object in the judgment image is respectively a sample sheet, a needle, or a columnar portion.

Here, in this embodiment, as learning images, SIM images and SEM images obtained in advance by irradiating a charged particle beam to an object are used. The charged particle beam is irradiated to the object from a predetermined direction. In the charged particle beam device 10, since the direction of the barrel of the charged particle beam irradiation system is fixed, the direction of irradiating the charged particle beam to the object is predetermined.

As an example, the information indicating the position of the object in the learning image is the 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, and the like.

The learning image includes both a SIM image and a SEM image of the object. The learning image is both a SIM image when the object is observed from an inclined direction after being tilted by a predetermined angle relative to the vertical direction of the sample stage 12, and a SEM image when the object is observed from the vertical direction of the sample stage 12. That is, the learning image includes an image when the object is observed from a first direction based on the sample stage 12, and an image when the object is observed from a second direction. The second direction is a direction different from the first direction based on the sample stage 12.

The learning unit 302 performs mechanical learning based on the learning data acquired by the learning data acquisition unit 301. The learning unit 302 stores the learning result in the memory unit 305 as a mechanical learning model M. The learning unit 302 performs mechanical learning for each type of object of the learning image included in the learning data. Therefore, a mechanical learning model M is generated for each type of object of the learning image included in the learning data. The mechanical learning model M is an example of a mechanical learning model obtained by learning the first information of the first image including the first object. In the following description, an object captured or depicted in an image may be referred to as an object of the image.

Here, the mechanical learning performed by the learning unit 302 refers to deep learning such as a convolutional neural network (CNN). In this case, the mechanical learning model M refers to a multi-layer neural network in which the weights between nodes change in accordance with the correspondence between the learning image and the position of the object in the learning image. The multi-layer neural network has 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 value of each pixel of the SIM and SEM images is input to the input layer, a set of values showing the position in the image is output from the output layer.

The judgment image acquisition unit 303 acquires a judgment image. The judgment image is a SIM image and a SEM image output from the control computer 22. The judgment image includes the image of the above-mentioned object. The object of the judgment image includes objects related to the irradiation of the charged particle beam, such as the sample piece Q and the used needle 18.

The judgment image is both a SIM image when the object is observed from an inclined direction tilted by a predetermined angle relative to the vertical direction of the sample stage 12, and a SEM image when the object is observed from the vertical direction of the sample stage 12. That is, the judgment image includes an image when the object is observed from a first direction, and an image when the object is observed from a second direction. Here, the first direction refers to a direction based on the sample stage 12, and the second direction refers to a direction different from the first direction based on the sample stage 12.

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 mechanical 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 pickup position of the sample 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.

In addition, the image processing computer 30 may acquire 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.

The following is a description of the automatic micro-sampling (MS: Micro-sampling) operation performed by the control computer 22, that is, the operation of automatically moving the sample piece Q formed by processing the sample S with a charged particle beam (beamed ion beam) to the sample piece holder P, which is roughly divided into the initial setting process, the sample piece picking process, and the sample piece installation process. (Initial setting process) Figure 7 is a diagram showing an example of the initial setting process of the present embodiment. Step S10: The control computer 22 sets the mode and processing conditions. The mode setting refers to the setting of the presence or absence of the posture control mode described later in response to the operator's input when the automatic sequence starts. The processing condition setting is the setting of the processing position, size, number of sample pieces Q, etc.

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.

In the present embodiment, the absorption current image data of the object is a combination of a SIM image of the object and a SEM image of the object. That is, the SIM image and the SEM image of the object are a combination of a SIM image when the object is observed from an inclined direction tilted by a predetermined angle relative to the vertical direction of the sample stage 12, and a SEM image when the object is observed from the vertical direction of the sample stage 12.

The determination image acquisition unit 303 acquires a SIM image or a 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 based on the mechanical learning model M. The determination unit 304 outputs position information indicating the determined position of the columnar portion 44 to the control computer 22.

Here, the determination unit 304 determines the two-dimensional coordinates on the sample stage 12 of the position of the object from the SIM image when the object is observed in the tilted direction after being tilted at a predetermined angle relative to the vertical direction of the sample stage 12. On the other hand, the determination unit 304 determines the two-dimensional coordinates of the position of the object on the plane perpendicular to the tilted direction from the SEM image when the object is observed in the tilted direction after being tilted at a predetermined angle relative to the vertical direction of the sample stage 12. The determination unit 304 determines the position of the object as a three-dimensional coordinate value based on the determined two-dimensional coordinates on the sample stage 12 and the two-dimensional coordinates on the plane perpendicular to the tilted direction.

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 device 10 and the direction information as the angle information between the two for calculation of the three-dimensional coordinate value. The determination unit 304 pre-stores the direction information in the storage unit 305 and reads it out, or obtains the direction information from the control computer 22. Here, in step S20, the object refers to the columnar portion 44. In the following process, the determination unit 304 determines the position of the object in the same way.

Here, referring to FIG. 8 to FIG. 12, the columnar portion 44 and the learning image of the columnar portion 44 used for generating the mechanical learning model M are explained. FIG. 8 and FIG. 9 are diagrams showing an example of the columnar portion 44 of the present embodiment. The columnar portion A0 shown in FIG. 8 and FIG. 9 is an example of the design structure of the columnar portion 44. Here, FIG. 8 is a top view of the columnar portion A0, and FIG. 9 is a side view of the columnar portion A0. The columnar portion A0 has a structure in which a support A01 of a step structure is bonded to a base A02.

FIG. 10 is a diagram showing an example of a learning image of the columnar portion 44 of the present embodiment. Learning images X11, X12, and X13 are used to learn the position of the columnar portion 44. In the learning images X11, X12, and X13, information showing the position of the columnar portion is shown as a circle. 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.

In addition, as an example, the learning image X11, the learning image X12, and the learning image X13 are learning images used to determine the position of the columnar portion 44 included in the SIM image and the SEM image when the columnar portion 44 is observed from the horizontal direction of the sample stage 12. In FIG. 2, although the focused ion beam irradiation optical system 14 and the electron beam irradiation optical system 15 do not face the sample stage 12 from the horizontal direction of the sample stage 12, either the focused ion beam irradiation optical system 14 or the electron beam irradiation optical system 15 may face the sample stage 12 from the horizontal direction, and the learning image X11, the learning image X12, and the learning image X13 are learning images used to determine the position of the columnar portion 44 in this case.

Fig. 11 is a diagram showing an example of a columnar portion 44 of the present embodiment in which the support does not form a stepped structure. The columnar portion A4 shown in Fig. 11 is a side view showing an example of a design structure of the columnar portion 44 in which the support does not form a stepped structure.

FIG. 12 is a diagram showing an example of a learning image of a columnar portion 44 in which the support of the present embodiment does not form a step structure. As an example, learning images X21, X22, and X23 are learning images for determining the position of the columnar portion 44 included in the SEM image when the columnar portion 44 is observed from the vertical direction of the sample stage 12. In learning images X21, X22, and X23, the shapes of support A51, support A61, and support 71 are different from each other. On the other hand, in learning images X21, X22, and X23, the shapes of base A52, base A62, and base A72 are the same.

In the previous template matching, when the shape of the pillars is different, the position of the columnar portion may not be determined. On the other hand, since the mechanical learning model M is generated based on mechanical learning using a learning image of the base including the columnar portion 44, in the mechanical learning model M, for example, the shape of the base is learned as a feature quantity. Therefore, in the charged particle beam device 10, even when the shape of the pillars is different, the determination accuracy of the columnar portion is improved. It is preferable that the object of the learning image includes a portion of the same shape between the object objects of the multiple learning images.

Return to FIG. 7 to continue the description of the initial setting process. 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. In addition, in the learning image of the columnar portion 44, it is preferable to include an image of the columnar portions located at both ends of the sample table 43 in the columnar portion 44. The image processing computer 30 distinguishes the columnar portions at both ends of the sample table 43 in the columnar portion 44 from the columnar portions other than the two ends for detection based on the mechanical learning model M generated using the learning data including the learning image. The control computer 22 can also calculate the inclination of the sample sheet holder P from the detected positions of the columnar portions at both ends. The control computer 22 may also correct the coordinate value of the position of the object based on the calculated inclination.

Step S30: The computer 22 controls the focused ion beam irradiation optical system 14 to process the sample S.

(Sample piece picking process) Figure 13 is a diagram showing an example of a sample piece picking process of the present embodiment. Here, picking refers to processing using a clustered ion beam or separating and removing the sample piece Q from the sample S using a needle.

Step S40: The control computer 22 adjusts the position of the sample. Here, the control computer 22 uses the stage drive mechanism 13 to move the sample stage 12 so that the sample piece Q as the target enters the viewpoint of the charged particle beam. Here, the control computer 22 uses the relative position relationship between the reference mark Ref and the sample piece Q. After moving the sample stage 12, the control computer 22 performs position alignment of the sample piece Q.

Step S50: The control computer 22 executes the movement of the needle 18. Here, referring to FIG. 14 , the processing for moving the needle 18 executed by the control computer 22 is described. FIG. 14 is a diagram showing an example of the movement processing of the needle 18 of the present embodiment. Steps S510 to 540 of FIG. 14 correspond to step S50 of FIG. 13 .

Step S510: The control computer 22 executes needle movement (coarse adjustment) to move the needle 18 using the needle driving mechanism 19. Step S520: The control computer 22 detects the tip of the needle 18. Here, the control computer 22 sends the absorption current image data including the needle 18 as the object to the image processing computer 30.

The determination image acquisition unit 303 acquires the SIM image and the 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 image acquired by the determination image acquisition unit 303 as the position of the object based on the mechanical learning model M. The determination unit 304 outputs position information indicating the determined position of the needle 18 to the control computer 22.

Next, the control computer 22 executes needle movement (fine adjustment) of moving the needle 18 by the needle driving mechanism 19 based on the position information indicating the position of the needle 18 determined by the image processing computer 30 .

Here, referring to FIGS. 15 to 18 , the needle 18 and the learning image of the needle 18 used for generating the mechanical learning model M are described. FIG. 15 is a diagram showing an example of SEM image data of the tip of the needle 18 of the present embodiment. FIG. 16 is a diagram showing an example of SIM image data of the tip of the needle 18 of the present embodiment.

Fig. 17 is a diagram showing an example of the tip of the needle 18 of the present embodiment. In Fig. 17, as an example of the needle 18, a needle B1 is shown when viewed from an inclined direction inclined at a predetermined angle with respect to the vertical direction of the sample stage 12.

FIG18 is a diagram showing an example of a learning image of the needle 18 involved in the present embodiment. Learning images Y31, Y32, and Y33 are used to learn the position of the tip of the needle 18. In the learning images Y31, Y32, and Y33, 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 thickness of the tip of the needle is different from each other. On the other hand, in the learning images Y31, Y32, and Y33, the shape of the tip of the needle is the same.

Regarding the actual thickness of the tip of the needle 18, the thickness varies due to cleaning. In the previous template matching, when the thickness of the tip of the needle is different, the position of the tip of the needle may not be determined. On the other hand, since the mechanical learning model M is generated based on mechanical learning using a learning image including the tip of the needle 18, in the mechanical learning model M, for example, the shape of the tip of the needle 18 is learned as a feature quantity. Therefore, in the charged particle beam device 10, even when the thickness of the tip of the needle is different, the determination accuracy of the tip of the needle is improved.

Returning to FIG. 14 , the description of the movement process of the needle 18 is continued. Step S530: The control computer 22 detects the pick-up position of the sample sheet Q. Here, the control computer 22 sends the SIM image and the SEM image of the sample sheet Q as the object to the image processing computer 30.

Here, with reference to FIG. 19 and FIG. 20, the sample piece Q and the learning image of the sample piece Q used for generating the mechanical learning model M are described. FIG. 19 is a diagram showing an example of SIM image data of the sample piece Q including the present embodiment. In FIG. 19, as an example of the sample piece Q, a sample piece Q71 and a circle showing a pick-up position are shown together.

FIG. 20 is a diagram showing an example of a learning image of a sample piece Q of the present embodiment. Learning images Z11, Z12, and Z13 are used to learn the position of the front end of the sample piece Q. In learning images Z11, Z12, and Z13, information showing the pickup position of the sample piece Q is shown as a circle. In learning images Z11, Z12, and Z13, the size and surface shape of the sample piece are different from each other. On the other hand, in learning images Z11, Z12, and Z13, the shape of the sample piece at the pickup position is the same.

The surface shape of an actual sample sheet is different for each individual. In the previous template matching, when the surface shape of the sample sheet is different, the pick-up position of the sample sheet may not be determined. In addition, in the previous template matching, when the contrast and focus between the image of the sample sheet and the template are different, the template matching may fail and the pick-up position of the sample sheet may not be determined. On the other hand, since the mechanical learning model M is generated based on mechanical learning using a learning image including the pick-up position of the sample sheet Q, in the mechanical learning model M, for example, the shape of the pick-up position of the sample sheet Q is learned as a feature quantity. Therefore, in the charged particle beam device 10, even when the surface shape of the sample sheet is different, the determination accuracy of the pick-up position of the sample sheet Q is improved.

Returning to FIG. 14 , the description of the movement process of the needle 18 is continued. Step S540: The control computer 22 moves the needle 18 to the detected pickup position. The control computer 22 terminates the movement process of the needle 18 as above.

Returning to FIG. 13 , the description of the sample sheet picking process is continued. Step S60: The control computer 22 connects the needle 18 to the sample sheet Q. Here, the control computer 22 uses a deposited film for connection. Step S70: The control computer 22 processes and separates the sample S and the sample sheet Q. Here, FIG. 21 shows the processing and separation, and is a diagram showing the cutting processing position T1 of the sample S and the support portion Qa of the sample sheet Q in the SIM image data of the embodiment of the present invention.

In addition, in this embodiment, the sample picking process and the sample mounting process can also be performed for the sample Q0 that has been processed in advance. In this case, the sample picking position designation of Q0 can be input into the control computer 22, and after the position adjustment of the sample transfer unit (needle 18) and the sample Q0, the cutting process position T1 of Figure 21 can be determined by mechanical learning. In the mechanical learning in this case, as the first image, an image showing the position (cutting process position) where the sample transfer unit approaches the sample in the sample extraction process of extracting the sample is used. In this case, the sample piece Q0 can be removed and separated even if the processing size and shape information showing the processing size and shape of the sample piece Q0 is not input to the control computer 22. In addition, after removing the sample piece Q0, the subsequent sample piece mounting process can also be performed in the same manner.

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.

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

(Sample sheet installation process) Figure 22 is a diagram showing an example of a sample sheet installation process of the present embodiment. Here, the sample sheet installation process refers to a process of transferring the removed sample sheet Q to the sample sheet holder P. Step S100: The control computer 22 determines the transfer position of the sample sheet Q. Here, the control computer 22 determines the specific columnar portion 44 registered in the above step S20 as the transfer position.

Step S110: The control computer 22 detects the position of the needle 18. Here, the control computer 22 detects the position of the front end of the needle 18 in the same manner as in the above-mentioned step S520. Step S120: The control computer 22 moves the needle 18. Here, the control computer 22 uses the needle drive mechanism 19 to move the needle 18 to the transfer position of the sample sheet Q determined in step S100. The control computer 22 leaves a predetermined gap between the columnar portion 44 and the sample sheet Q and stops the needle 18.

Step S130: The control computer 22 connects the sample sheet Q connected to the needle 18 to the columnar portion 44. Step S140: The control computer 22 separates the needle 18 from the sample sheet Q. Here, the control computer 22 separates by cutting the deposited film DM2 connecting the needle 18 and the sample sheet Q. Step S150: The control computer 22 causes the needle 18 to retreat. Here, the control computer 22 uses the needle driving mechanism 19 to cause the needle 18 to move away from the sample sheet Q by a predetermined distance.

Step S160: The control computer 22 determines whether to execute the next sampling. Here, executing the next sampling means continuing sampling from a different position of the same sample S. Since the setting of the number to be sampled is registered in advance in step S10, the control computer 22 confirms the data and then determines whether to execute the next sampling. When it is determined to execute the next sampling, the control computer 22 returns to step S50 and continues the subsequent steps as described above to execute the sampling operation. On the other hand, when the control computer 22 determines not to execute the next sampling, a series of processes of the automatic MS are terminated.

In addition, in the present embodiment, an example is described in which the learning data is a combination of a learning image and information indicating the position of an object in the learning image, but the present invention is not limited to this. In addition to the learning image, the learning data may also include parameter information such as the type of sample, scanning parameters (accelerating voltage of the focused ion beam irradiation optical system 14 and the electron beam irradiation optical system 15), the number of times the needle 18 has been used after cleaning, and whether foreign matter is attached to the tip of the needle 18.

In this case, the mechanical learning model M1 is generated by executing mechanical learning based on the learning image and parameter information. In addition, the determination unit 304 obtains parameter information in addition to the image data of the SIM image and the SEM image from the control computer 22, and determines the position of the object in the image based on the image data, the parameter information, and the mechanical learning model M1.

In addition, the parameter information may also include the above-mentioned direction information. When the learning data includes the direction information, the relationship between the object and the direction of observing the object (the direction based on the sample stage 12) is learned to generate the mechanical learning model M1, so the determination unit 304 does not need to use the direction information in determining the position of the object.

In addition, as described above, the computer (the control computer 22 in the present embodiment) controls the position related to the second object (the columnar portion 44, the needle 18, and the sample piece Q in the present embodiment) by determining the result of the position related to the second object (the columnar portion 44, the needle 18, and the sample piece Q in the present embodiment) based on the model (the mechanical learning model M1 in the present embodiment) 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 sample piece Q in the present embodiment) of the image processing computer 30. In addition, the image processing computer 30 and the control computer 22 can also be integrally provided in the charged particle beam device 10.

(Second embodiment) The second embodiment of the present invention is described in detail below with reference to the attached drawings. In this embodiment, a simulation image generated in accordance with the type of object is used as a learning image, or a mechanical learning model to be used is selected in accordance with the type of object. The charged particle beam device 10 of this embodiment is referred to as a charged particle beam device 10a, and the image processing computer 30 is referred to as an image processing computer 30a.

FIG23 is a diagram showing an example of the structure of the image processing computer 30a of the present embodiment. Comparing the image processing computer 30a of the present embodiment (FIG23) with the image processing computer 30 of the first embodiment (FIG6), the learning image generation unit 306a, the classification unit 307a, the mechanical learning model M1a, and the classification learning model M2a are different. Here, the functions of other components are the same as those of the first embodiment. The description of the same functions as the first embodiment is omitted, and in the second embodiment, the description is centered on the parts that are different from the first embodiment. The control unit 300a includes a learning data acquisition unit 301, a learning unit 302, a determination image acquisition unit 303, and a determination unit 304, as well as a learning image generation unit 306a and a classification unit 307a.

The learning image generation unit 306a generates a simulation image PI as a learning image. In this embodiment, the simulation image PI is an image generated based on a SIM image and a SEM image previously obtained by irradiating a charged particle beam to an object. As an example, the learning image generation unit 306a generates the simulation image PI based on a bare object BW and a pattern image PT.

Bare BW refers to an image showing the shape of an object by removing the surface pattern from the object. Bare BW is preferably a plurality of images showing the shapes of a plurality of objects with different sizes, contrasts, focuses, etc. Bare BW is an image drawn using imaging software, unlike SIM images and SEM images. Pattern image PT refers to an image showing a pattern corresponding to the internal structure of the object. Pattern image PT can be a SIM image or SEM image obtained by irradiation with a charged particle beam, or an image drawn using imaging software.

The learning image generation unit 306a generates a simulation image PI by applying random noise to a pattern corresponding to the internal structure of the object shown in the pattern image PT using a simulation image generation algorithm and superimposing the pattern on the bare object BW.

In the present embodiment, the case where the learning image generating unit 306a generates the simulation image PI as the learning image of the sample piece Q is described as an example, but the present invention is not limited to this. The learning image generating unit 306a may generate the simulation image PI as the learning image of the needle 18 and the columnar portion 44.

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

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

Here, referring to FIG. 24 to FIG. 26, the method for generating the simulation image PI is described. FIG. 24 is a diagram showing an example of a bare part BW of the present embodiment. In FIG. 24, bare parts BW1, bare parts BW2, and bare parts BW3 are shown as bare parts BW of the sample piece Q. Bare parts BW1, bare parts BW2, and bare parts BW3 are images simulating the shapes of the sample pieces Q of multiple sizes. In addition, bare parts BW1, bare parts BW2, and bare parts BW3 each include an image corresponding to the needle 18 as information showing the pickup position.

FIG. 25 is a diagram showing an example of a pattern image PT of the present embodiment. FIG. 25 shows a user sample U1 as a pattern image PT. The user sample U1 is an image prepared in advance in accordance with the type of sample piece Q to be processed by the user of the charged particle beam device 10a. In the user sample U1, for a sample piece composed of a plurality of layers, a pattern corresponding to the type of material constituting these plurality of layers is depicted.

Fig. 26 is a diagram showing an example of a simulation image PI of the present embodiment. Fig. 26 shows, as simulation images PI, simulation images PI1, PI2, and PI3 generated based on the bare parts BW1, BW2, and BW3 of Fig. 24 and the user sample U1 of Fig. 25. The simulation images PI1, PI2, and PI3 overlap the pattern of the internal structure shown in the user sample U1 on the shape of the sample piece Q of multiple sizes.

Returning to FIG. 23, the structure of the image processing computer 30a is further described. The classification unit 307a classifies the judgment image acquired by the judgment image acquisition unit 303 based on the classification learning model M2a. Here, the classification unit 307a may not necessarily classify the judgment image. Whether the classification unit 307a classifies the judgment image is set in the image processing computer 30, for example, in response to the setting input to the control computer 22. The classification learning model M2a is a model for selecting a model for the judgment unit 304 to use for judgment from the plurality of models included in the mechanical learning model M1a in response to the type of the object. Here, the plurality of models included in the machine learning model M1a are differentiated not only according to the learning data set used for generating the model, but also according to the machine learning algorithm.

For example, the classification learning model M2a associates the type of sample Q processed by each user with the model included in the machine learning model M1a. The classification learning model M2a is generated in advance based on machine learning and stored in the storage unit 305.

Next, referring to FIG. 27 , the process of detecting the pickup position of the sample piece Q as the action of the automatic MS of the charged particle beam device 10a using the classification learning model M2a is described. FIG. 27 is a diagram showing an example of the detection process of the pickup position of the present embodiment. Step S310: The classifier 307a classifies the determination image acquired by the determination image acquisition unit 303 based on the classification learning model M2a. Step S320: The classifier 307a selects the mechanical learning model used by the determination unit 304 in the determination from the plurality of models included in the mechanical learning model M1a according to the classification result. 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.

In addition, in the above-mentioned embodiment, an example is described in which the charged particle beam device 10, 10a has two charged particle beam irradiation optical systems, namely the focused ion beam irradiation optical system 14 and the electron beam irradiation optical system 15, but it is not limited to this. The charged particle beam device may also have a charged particle beam irradiation optical system. In this case, it is preferable that in the judgment image obtained by the charged particle beam irradiation through the charged particle beam irradiation optical system, for example, in addition to reflecting the object, the shadow of the object is also reflected. In addition, in this case, the object is a needle 18.

The shadow of the needle 18 refers to a phenomenon that occurs when the needle 18 approaches the surface of the sample piece Q and blocks the secondary electrons (or secondary ions) generated from the surface of the sample piece Q near the needle 18 from reaching the detector 16 when observed from an inclined direction inclined at a predetermined angle relative to the vertical direction of the sample stage 12. The closer the distance between the needle 18 and the surface of the sample piece Q is, the more obvious this phenomenon is. Therefore, the closer the distance between the needle 18 and the surface of the sample piece Q is, the higher the brightness value of the shadow in the judgment image is.

The image processing computer 30 not only performs determination by setting the position of the tip of the needle 18 as a two-dimensional coordinate in the determination image, but also calculates the distance between the tip of the needle 18 and the surface of the sample sheet Q from the brightness value of the shadow of the needle 18. Thus, the image processing computer 30 performs determination by setting the position of the tip of the needle 18 as a three-dimensional coordinate value from the determination image.

In addition, in the above-mentioned embodiment, the control computer 22 may generate absorption current image data by setting the scanning speed to a second speed slower than the first speed, and the image processing computer 30 may set the resolution of the image contained 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 determine the position of the object based on the mechanical learning model M. Here, the scanning speed refers to the speed of scanning the irradiation position of the charged particle beam in the process of generating the absorption current image data by the control computer 22. The first speed refers to, for example, the speed at which the irradiation position of the charged particle beam is scanned by a previous charged particle beam device. The second speed is an arbitrary speed slower than the first speed. The second speed is, for example, a scanning speed selected in a previous charged particle beam device in order to obtain a high-precision image for improving the success rate of template matching. Resolution refers to the density of pixels constituting an image. The first resolution refers to, for example, the resolution of a SIM image and a SEM image included in absorption current image data generated in a previous charged particle beam device. The second resolution refers to any resolution having a higher spatial frequency than the first resolution. 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". In addition, "converting the resolution of an image from the first resolution to the second resolution" is also referred to as "super-resolutioning the image".

Here, the control computer 22 sets the scanning speed to a low speed to generate absorption current image data, the image processing computer 30 sets the scanning speed to a low speed to generate the absorption current image data, performs super-resolution on the resolution of the SIM image and the SEM image included in the absorption current image data, and then determines the position of the object based on the mechanical learning model M. This processing is performed in the above-mentioned step S20 shown in FIG. 7, step S520 shown in FIG. 14, step S110 shown in FIG. 22, etc.

The judgment image acquisition unit 303 acquires SIM images and SEM images from the image processing computer 30 as judgment images. These SIM images and SEM images are images included in the absorption current image data generated by the control computer 22 setting the scanning speed to a low speed. The judgment unit 304 performs super-resolution processing on the judgment image acquired by the judgment image acquisition unit 303. For the super-resolution technology used by the judgment unit 304 in super-resolution, any super-resolution technology can be used without limitation. The judgment 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 judgment unit 304 not only converts the resolution of the SIM image and the SEM image, but also performs processing to make the spatial frequency of the image of the object contained in the SIM image and the SEM image higher than the spatial frequency of the image before conversion. The determination unit 304 determines the position of the object included in the super-resolution determination image based on the machine learning model M. The determination unit 304 outputs position information indicating the determined position of the object to the control computer 22 .

As described above, when the control computer 22 sets the scanning speed to the second speed which is slower than the first speed to generate absorption current image data, and the image processing computer 30 sets the resolution of the image contained in the absorption current image data generated by setting the scanning speed to the second speed to the second resolution which is higher than the first resolution, and then when the position of the object is determined based on the mechanical learning model M, when the scanning speed is set to the second speed, the processing time for determining the position of the object can be shortened and the determination accuracy can be improved compared to the case where the resolution of the image is not set to the second resolution.

In addition, the control computer 22 may perform super-resolution on the absorption current image data obtained by setting the scanning speed to the second speed, and then determine the position of the object based on the mechanical learning model M. As a result, if the position of the object cannot be determined, the scanning speed is set to the first speed and the absorption current image data is obtained, and the position of the object is determined based on the mechanical learning model M without super-resolution. If the reason why the position of the object cannot be determined is that the super-resolution is insufficient, there is a possibility that the position of the object can be correctly detected by performing a retry process using the absorption current image data obtained by setting the scanning speed to the first speed.

In addition, a part of the control computer 22 and the image processing computers 30 and 30a in the above-mentioned embodiment, such as the learning data acquisition unit 301, the learning unit 302, the judgment image acquisition unit 303, the judgment unit 304, the learning image generation unit 306a, and the classification unit 307a, can also be realized by a computer. In this case, it is also possible to realize the control function by recording the program for realizing the control function in a recording medium that can be read by a computer, and making the computer system read the program recorded in the recording medium and execute it. In addition, the "computer system" mentioned here is a computer system built into the control computer 22 and the image processing computer 30 and 30a, including hardware such as OS and peripheral devices. In addition, "computer-readable recording media" refers to removable media such as floppy disks, optical disks, ROMs, CD-ROMs, and storage devices such as hard disks built into computer systems. Furthermore, "computer-readable recording media" may also include a structure that dynamically retains programs for a short period of time, such as a communication line when sending programs through a network such as the Internet or a communication line such as a telephone line, or a structure that retains programs for a certain period of time, such as a volatile memory inside a computer system that serves as a server or user end in this case. In addition, the above program may be a program for realizing a part of the above functions, or a program that can realize the above functions by combining with a program already recorded in the computer system. In addition, part or all of the control computer 22 and the image processing computer 30, 30a in the above-mentioned embodiment may be implemented as an integrated circuit such as LSI (Large Scale Integration). Each functional block of the control computer 22 and the image processing computer 30, 30a may be individually processed, or part or all of them may be integrated and processed. In addition, the method of integrated circuitization is not limited to LSI, and it may be implemented using a dedicated circuit or a general-purpose processor. In addition, in the case where an integrated circuitization technology that replaces LSI appears due to the progress of semiconductor technology, an integrated circuit based on the technology may also be used.

An embodiment of the present invention has been described in detail above with reference to the drawings, but the specific structure is not limited to the above-mentioned embodiment, and various design changes can be made within the scope of the gist of the present invention.

10,10a: Charged particle beam device S: Sample Q: Sample sheet 14: Focused ion beam irradiation optical system (charged particle beam irradiation optical system) 15: Electron beam irradiation optical system (charged particle beam irradiation optical system) 12: Sample stage 18: Needle (sample sheet transfer unit) 19: Needle drive mechanism (sample sheet transfer unit) P: Sample sheet holder 12a: Holder fixing table 22: Control computer (computer)

[FIG. 1] is a diagram showing an example of the structure of a charged particle beam device and an image processing computer according to the first embodiment of the present invention. [FIG. 2] is a diagram showing an example of the structure of a charged particle beam device according to the first embodiment of the present invention. [FIG. 3] is a top view of a sample sheet according to the first embodiment of the present invention. [FIG. 4] is a top view of a sample sheet holder according to the first embodiment of the present invention. [FIG. 5] is a side view of a sample sheet holder according to the first embodiment of the present invention. [FIG. 6] is a diagram showing an example of the structure of an image processing computer according to the first embodiment of the present invention. [FIG. 7] is a diagram showing an example of the initial setting process of the first embodiment of the present invention. [FIG. 8] is a top view of a columnar portion according to the first embodiment of the present invention. [Fig. 9] is a side view of the columnar portion of the first embodiment of the present invention. [Fig. 10] is a diagram showing an example of a learning image of the columnar portion of the first embodiment of the present invention. [Fig. 11] is a diagram showing an example of a columnar portion of the first embodiment of the present invention where the pillars do not form a stepped structure. [Fig. 12] is a diagram showing an example of a learning image of the columnar portion of the first embodiment of the present invention where the pillars do not form a stepped structure. [Fig. 13] is a diagram showing an example of a sample sheet picking process of the first embodiment of the present invention. [Fig. 14] is a diagram showing an example of a needle moving process of the first embodiment of the present invention. [Fig. 15] is a diagram showing an example of SEM image data including the tip of the needle of the first embodiment of the present invention. [FIG. 16] is a diagram showing an example of SIM image data including the tip of the needle of the first embodiment of the present invention. [FIG. 17] is a diagram showing an example of the tip of the needle of the first embodiment of the present invention. [FIG. 18] is a diagram showing an example of a learning image of the needle of the first embodiment of the present invention. [FIG. 19] is a diagram showing an example of SIM image data including a sample sheet of the first embodiment of the present invention. [FIG. 20] is a diagram showing an example of a learning image of a sample sheet of the first embodiment of the present invention. [FIG. 21] is a diagram showing the cutting processing position of the sample and the support portion of the sample sheet in the SIM image data of the first embodiment of the present invention. [FIG. 22] is a diagram showing an example of a sample sheet mounting process of the first embodiment of the present invention. [Figure 23] is a diagram showing an example of the structure of an image processing computer of the second embodiment of the present invention. [Figure 24] is a diagram showing an example of a bare part of the second embodiment of the present invention. [Figure 25] is a diagram showing an example of a pattern image of the second embodiment of the present invention. [Figure 26] is a diagram showing an example of a simulation image of the second embodiment of the present invention. [Figure 27] is a diagram showing an example of a detection process of a pickup position of the second embodiment of the present invention.

10: Charged particle beam device

22: Control computer (computer)

30: Computer for image processing

M: Machine learning model

Claims (7)

A charged particle beam device that automatically produces a sample sheet from a sample, the charged particle beam device comprising: a charged particle beam irradiation optical system that irradiates a charged particle beam; a sample stage that carries and moves the sample; a sample sheet transfer unit that holds and transports the sample sheet separated and removed from the sample; a holder fixing table that holds and transfers the sample sheet; and a computer that controls the position related to a second object based on a mechanical learning model that learns first information including a first image of a first object and second information including a second image obtained by irradiation with the charged particle beam; the second object includes the sample sheet; and the first image includes an image showing the shape of the sample before separation and removal of the sample sheet. According to the charged particle beam device described in claim 1, the second object includes a portion of a sample table provided in the sample holder. The charged particle beam device according to claim 1 or 2, wherein the second object includes a needle used for the sample sheet transfer unit. According to the charged particle beam device described in claim 1 or 2, the first image is an image showing a position where the sample piece transfer unit is brought close to the sample piece in a sample removal process for removing the sample piece. The charged particle beam device according to claim 1 or 2, wherein the first image is an image showing the position where the sample piece is separated and removed from the sample. The charged particle beam device according to claim 1 or 2, wherein the first image is a simulated image generated in response to the type of the second object. The charged particle beam device according to claim 1 or 2, wherein the type of the first object is the same as the type of the second object.

Images