Charged particle beam device

Abstract

Provided is a charged particle beam device which achieves removal of a foreign matter adhering to the most distal end of a needle. The charged particle beam device comprises: a charged particle beam emission optical system that emits a charged particle beam; a sample piece relocation means provided with a sample stage that is moved while having the sample placed thereon, a needle that holds and transports a sample piece separated and extracted from the sample, and a needle drive mechanism that drives the needle; a holder fixing bed that holds a sample piece holder to which the sample piece is to be relocated; a machine learning model that has learned information including an image of the needle; and a computer that controls the charged particle beam emission optical system to process an object on the basis of the determination of the machine learning model.

Description

charged particle beam device

[0001] The present disclosure relates to a charged particle beam device, and in particular to a technique that is effective when applied to a charged particle beam device having a needle.

[0002] Patent Document 1 proposes a charged particle beam device in which a specimen is irradiated with an ion beam to produce a specimen, which is then extracted and transferred to a specimen holder for observation with a transmission electron microscope.

[0003] In charged particle beam devices, needles are used to extract sample pieces processed by ion beam irradiation. The tip of the needle may change shape due to adhesion or cutting of the sample piece, or foreign matter may adhere to the tip. In such cases, a cleaning process is performed using the ion beam to reshape the needle tip.

[0004] Patent document 1 discloses a technology for creating a desired fixed shape by using image processing technology to recognize the shape of the needle tip, setting a rectangular processing frame in the area outside the upper and lower edges of the needle, and performing ion beam processing.

[0005] Japanese Patent Application Laid-Open No. 2020-139958

[0006] However, in the above-described cleaning process, there are cases where deposits remain on the tip of the needle or the needle shape is deformed, making it impossible to use a needle with an optimal shape for transferring the sample piece. Patent Document 2 does not disclose or suggest machine learning about deposits on the tip of the needle.

[0007] The present disclosure provides a charged particle beam device that makes it possible to provide a needle with an optimum shape for transferring a sample piece.

[0008] Other objects and novel features will become apparent from the description of this specification and the accompanying drawings.

[0009] A brief summary of representative aspects of this disclosure is as follows.

[0010] According to one embodiment, the charged particle beam device comprises: a charged particle beam irradiation optical system that irradiates a charged particle beam; a sample stage that places a sample on it and moves it; a sample piece transfer means that includes a needle that holds and transports a sample piece to be separated and extracted from the sample; and a needle driving mechanism that drives the needle; a holder fixing table that holds a sample piece holder to which the sample piece is transferred; a machine learning model that has learned information including an image of the needle; and a computer that controls the charged particle beam irradiation optical system to process an object based on the judgment of the machine learning model.

[0011] According to the charged particle beam device according to the embodiment, it is possible to process a needle into a shape that is optimal for transferring a sample piece.

[0012] 1 is a diagram showing an example of the configuration of a charged particle beam system and an image processing computer according to an embodiment. FIG. 1 is a diagram showing an example of the configuration of a charged particle beam system according to an embodiment. FIG. 2 is a plan view showing a sample piece according to an embodiment. FIG. 3 is a plan view of a sample piece holder according to an embodiment. FIG. 4 is a side view of a sample piece holder according to an embodiment. FIG. 5 is a diagram showing an example of the configuration of an image processing computer according to an embodiment. FIG. 6 is a diagram showing an example of an initial setting process according to an embodiment. FIG. 7 is a top view of a columnar portion according to an embodiment. FIG. 8 is a side view of a columnar portion according to an embodiment. FIG. 9 is a diagram showing an example of a learning image of a columnar portion according to an embodiment. FIG. 10 is a diagram showing an example of a columnar portion in which pillars do not have a stepped structure according to an embodiment. FIG. 11 is a diagram showing an example of a learning image of a columnar portion in which pillars do not have a stepped structure according to an embodiment. FIG. 12 is a diagram showing an example of a sample piece pick-up process according to an embodiment. FIG. 13 is a diagram showing an example of a needle movement process according to an embodiment. FIG. 14 is a diagram showing an example of SEM image data including the tip of a needle according to an embodiment. FIG. 15 is a diagram showing an example of SIM image data including the tip of a needle according to an embodiment. FIG. 16 is a diagram showing an example of a needle tip according to an embodiment. FIG. 17 is a diagram showing an example of SIM image data including a sample piece according to an embodiment. FIG. 18 is a diagram showing an example of a learning image of a sample piece according to an embodiment. FIG. 19 is a diagram showing cutting processing positions of a sample and a support portion of the sample piece in the SIM image data according to an embodiment. FIG. 19 is a diagram showing an example of a sample piece mounting process according to an embodiment. 26A and 26B are diagrams illustrating an example of a needle trimming process according to an embodiment; FIG. 27A is a diagram illustrating an example of a learning image of a needle according to an embodiment; FIG. 27B is a diagram illustrating an example of a learning image of a needle whose tip thickness has changed due to cleaning according to an embodiment; FIG. 27C is a diagram illustrating an example of an original image of a needle with foreign matter adhering thereto according to an embodiment; FIG. 27D is a diagram illustrating an example of a teacher image showing a foreign matter region in the original image of FIG. 26 according to an embodiment; FIG. 27E is a diagram illustrating an example of an original image in which the contrast, angle, magnification, position, etc. of the needle have been changed according to an embodiment; FIG. 27F is a diagram illustrating an example of one set of learning data of an original image in which foreign matter has adhered to the tip portion of a needle whose tip thickness has changed due to cleaning according to an embodiment, and the teacher image; FIG. 27F is a diagram illustrating an example of a learning model for determining whether needle cleaning is necessary according to an embodiment;Fig. 10 is a diagram for explaining an example of a processing frame according to a comparative example; Fig. 11 is a diagram for explaining a problem of the processing frame according to the comparative example; Fig. 12 is a diagram for explaining an example of a processing frame according to an embodiment; Fig. 13 is a diagram for explaining a setting example of a processing frame according to an embodiment; Fig. 14 is a diagram for explaining shaping of a needle according to an embodiment.

[0013] Hereinafter, examples will be described with reference to the drawings. However, in the following description, the same components will be assigned the same reference numerals, and repeated explanations may be omitted. Note that the drawings may be more schematic than the actual embodiment to make the description clearer, but they are merely examples and do not limit the interpretation of the present disclosure.

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will now be described in detail with reference to the accompanying drawings. Fig. 1 is a diagram showing an example of the configuration of a charged particle beam system 10 and an image processing computer 30 according to this embodiment.

[0015] A control computer 22 provided in the charged particle beam device 10 acquires image data obtained by irradiating the charged particle beam. The control computer 22 transmits and receives data to and from an image processing computer 30. The image processing computer 30 determines the object included in the image data received from the control computer 22 based on a machine learning model M. Based on the determination result of the image processing computer 30, the control computer 22 controls the position of the object and removes foreign matter adhering to the tip of the needle, etc.

[0016] The control computer 22 is an example of a computer that controls the position of a second object based on a machine learning model that has learned first information including a first image of the first object and second information including a second image acquired by irradiating the first object with a charged particle beam. Note that the image processing computer 30 may be provided in the charged particle beam device 10.

[0017] (Overall Configuration of Charged Particle Beam System) Next, the configuration of the charged particle beam system 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the charged particle beam system 10 according to an embodiment.

[0018] The charged particle beam device 10 includes a sample chamber 11, a sample stage 12, a stage driving mechanism 13, a focused ion beam irradiation optical system (also called a charged particle 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.

[0019] The sample chamber 11 maintains a vacuum state inside. The sample stage 12 fixes the sample S and the sample piece holder P inside the sample chamber 11. The sample stage 12 includes a holder fixing base 12a that holds the sample piece holder P. The holder fixing base 12a may be configured to be able to mount a plurality of sample piece holders P.

[0020] The stage driving mechanism 13 drives the sample stage 12. The stage driving mechanism 13 is housed inside the sample chamber 11 while connected to the sample stage 12, and displaces the sample stage 12 about a predetermined axis in response to a control signal output from the control computer 22. The stage driving mechanism 13 includes a movement mechanism 13a that moves the sample stage 12 parallel to at least the X-axis and Y-axis that are parallel to the horizontal plane and perpendicular to each other, and the Z-axis that is perpendicular to the X-axis and Y-axis. The stage driving mechanism 13 also includes a tilt mechanism 13b that tilts the sample stage 12 about the X-axis or Y-axis, and a rotation mechanism 13c that rotates the sample stage 12 about the Z-axis.

[0021] The focused ion beam irradiation optical system 14 irradiates a focused ion beam (FIB) onto an irradiation target within a predetermined irradiation region (i.e., scanning range) inside the sample chamber 11. Here, the focused ion beam irradiation optical system 14 irradiates the focused ion beam vertically from above downward onto irradiation targets such as the sample S placed on the sample stage 12, the sample piece Q, and the needle 18 present within the irradiation region.

[0022] The focused ion beam irradiation optical system 14 includes an ion source 14 a that generates ions and an ion optical system 14 b that focuses and deflects the ions extracted from the ion source 14 a. The ion source 14 a and the ion optical system 14 b are controlled in response to control signals output from a control computer 22, and the irradiation position and irradiation conditions of the focused ion beam are controlled by the control computer 22.

[0023] The electron beam irradiation optical system 15 irradiates an electron beam (EB) onto an irradiation target within a predetermined irradiation region inside the sample chamber 11. Here, the electron beam irradiation optical system 15 can irradiate irradiation targets such as the sample S fixed on the sample stage 12, the sample piece Q, and the needle 18 present within the irradiation region with the electron beam from above downward in an inclined direction at a predetermined angle (e.g., 60°) with respect to the vertical direction.

[0024] The electron beam irradiation optical system 15 includes an electron source 15 a that generates electrons and an electron optical system 15 b that focuses and deflects the electrons emitted from the electron source 15 a. The electron source 15 a and the electron optical system 15 b are controlled in response to control signals output from a control computer 22, and the control computer 22 controls the irradiation position and irradiation conditions of the electron beam, etc.

[0025] The positions 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 arranged vertically and the focused ion beam irradiation optical system 14 being arranged in an inclined direction at a predetermined angle relative to the vertical direction.

[0026] The detector 16 detects secondary charged particles (secondary electrons, secondary ions) R generated from the irradiation target by irradiation with the focused ion beam or electron beam. The gas supply unit 17 supplies gas G to the surface of the irradiation target. The needle 18 removes a minute sample piece Q from the sample S fixed on the sample stage 12, holds the sample piece Q, and transfers it to the sample piece holder P. The needle driving mechanism 19 drives the needle 18 to transport the sample piece Q. Hereinafter, the needle 18 and the needle driving mechanism 19 may be collectively referred to as a sample piece transfer means.

[0027] The absorption current detector 20 detects the inflow current (also called absorption current) of the charged particle beam flowing into the needle 18 and outputs the detected result to the control computer 22 as an inflow current signal.

[0028] The control computer 22 controls at least the stage driving 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 driving mechanism 19. The control computer 22 is disposed outside the sample chamber 11, and is connected to a display device 21 and an input device 23 such as a mouse or keyboard that outputs signals in response to input operations by an operator. The control computer 22 comprehensively controls the operation of the charged particle beam instrument 10 using signals output from the input device 23 or signals generated by a preset automatic operation control process.

[0029] 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 includes a communication interface for communicating with the image processing computer 30.

[0030] The control computer 22 also visualizes the inflow current signal output from the absorbed current detector 20 as absorbed current image data. The control computer 22 converts the amount of secondary charged particles R detected by the detector 16 while scanning the irradiation position of the charged particle beam into a brightness signal associated with the irradiation position, and generates absorbed current image data that indicates the shape of the irradiation target based on the two-dimensional position distribution of the detected amount of secondary charged particles R. In the absorbed current image mode, the control computer 22 detects the absorbed current flowing through the needle 18 while scanning the irradiation position of the charged particle beam, and generates absorbed current image data that indicates the shape of the needle 18 based on the two-dimensional position distribution of the absorbed current (absorbed current image). The control computer 22 displays on the display device 21 each of the generated image data, as well as a screen for performing operations such as enlarging, reducing, moving, and rotating each of the image data. The computer 22 also displays on the display device 21 a screen for performing various settings, such as mode selection and processing settings, in automatic sequence control.

[0031] The display device 21 displays image data based on the secondary charged particles R detected by the detector 16 .

[0032] The image processing computer 30 also takes in the image data generated by the control computer 22, identifies the area of ​​foreign matter adhering to the needle 18, and transmits coordinate information of the area to the control computer 22. The control computer 22 sets up a processing frame that defines the operation area of ​​the charged particle beam according to the coordinates of the foreign matter area received from the image processing computer 30.

[0033] The charged particle beam device 10 irradiates the surface of an object to be irradiated with a focused ion beam while scanning it, thereby enabling imaging of the object to be irradiated, various processes by sputtering (drilling, trimming, etc.), and formation of a deposition film.

[0034] FIG. 3 is a plan view showing a sample piece Q formed by irradiating the surface (hatched area) of the sample S with a focused ion beam in the charged particle beam device 10 according to the embodiment, before being extracted from the sample S. The symbol F indicates the processing frame by the focused ion beam, i.e., the scanning range of the focused ion beam, and the area inside (white area) indicates the processing region H excavated by sputtering processing using the focused ion beam. The reference mark Ref is a reference point indicating the position where the sample piece Q will be formed (remaining without being excavated). A deposition film is used to determine the approximate position of the sample piece Q, and a microhole is used for precise alignment. The sample piece Q has been etched so that the peripheral portions on the side and bottom sides are removed, leaving a support portion Qa connected to the sample S, and the sample piece Q is cantilevered on the sample S by the support portion Qa.

[0035] Next, the test piece holder P will be described with reference to FIGS.

[0036] Fig. 4 is a plan view of the specimen holder P, and Fig. 5 is a side view. The specimen holder P includes a substantially semicircular plate-shaped base 42 having a notch 41, and a specimen stage 43 fixed to the notch 41. The base 42 is formed of a circular metal plate, for example. The specimen stage 43 is comb-shaped and includes a plurality of spaced-apart protruding columnar portions (hereinafter also referred to as pillars) 44 onto which the specimen Q is transferred.

[0037] (Image Processing Computer) Next, the image processing computer 30 will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the configuration of the image processing computer 30 according to this embodiment.

[0038] The image processing computer 30 includes a control unit 300 and a storage unit 305 .

[0039] 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 .

[0040] The training data acquisition unit 301 acquires training data. The training data is information used for machine learning training. The training data is a set of a training image and information indicating the position of an object in the training image. Examples of objects in the training image include a sample piece, a needle, a foreign substance attached to the tip of the needle, and a columnar portion provided on a sample piece holder. Here, the type of object in the training image is the same as the type of object in the determination image. For example, if the type of object in the training image is a sample piece, a needle, a foreign substance attached to the tip of the needle, or a columnar portion, the type of object in the determination image is the sample piece, the needle, a foreign substance attached to the tip of the needle, or a columnar portion, respectively.

[0041] In this embodiment, the training images are SIM images or SEM images obtained in advance by irradiating a target with a charged particle beam. The charged particle beam is irradiated onto the target from a predetermined direction. In the charged particle beam device 10, the direction of the lens barrel of the charged particle beam irradiation system is fixed, so the direction in which the charged particle beam irradiates the target is determined in advance.

[0042] The information indicating the position of the object in the training image is, for example, coordinates indicating the position of the object in the training image, such as two-dimensional Cartesian coordinates or polar coordinates.

[0043] The training images include both SIM images and SEM images of the object. The training images are both SIM images of the object viewed from an inclined direction at a predetermined angle with respect to the vertical direction of the sample stage 12, and SEM images of the object viewed from the vertical direction of the sample stage 12. In other words, the training images include an image of the object viewed from a first direction relative to the sample stage 12, and an image of the object viewed from a second direction. The second direction is a direction different from the first direction relative to the sample stage 12.

[0044] The learning unit 302 performs machine learning based on the training data acquired by the training data acquisition unit 301. The learning unit 302 stores the results of the learning in the storage unit 305 as a machine learning model M. The learning unit 302 performs machine learning for each type of object in the training images included in the training data. Therefore, a machine learning model M is generated for each type of object in the training images included in the training data. The machine learning model M is an example of a machine learning model in which first information including a first image of a first object is learned. Note that in the following description, an object captured or drawn in an image may be referred to as the object of the image.

[0045] Here, the machine learning performed by the learning unit 302 is, for example, deep learning using a convolutional neural network (CNN). In this case, the machine learning model M is a multi-layer neural network in which the weights between nodes are changed according to the correspondence between a training image and the position of an object within the training image. This 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 within the image. When the brightness value of each pixel in a SIM image or SEM image is input to the input layer, a set of values ​​indicating the position within the image is output from the output layer.

[0046] The determination image acquisition unit 303 acquires a determination image. The determination image is a SIM image or SEM image output from the control computer 22. The determination image includes an image of the object described above. The object of the determination image includes an object related to the irradiation of the charged particle beam, such as the sample piece Q, the used needle 18, or foreign matter attached to the tip of the needle 18.

[0047] The determination image is both a SIM image of the object viewed from a direction inclined at a predetermined angle with respect to the vertical direction of the sample stage 12, and a SEM image of the object viewed from the vertical direction of the sample stage 12. In other words, the determination image includes an image of the object viewed from a first direction and an image of the object viewed from a second direction. Here, the first direction is a direction based on the sample stage 12, and the second direction is a direction different from the first direction based on the sample stage 12.

[0048] 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 learned by the learning unit 302. The position of the object included in the determination image includes, for example, the pickup position of the sample piece in the SIM image or SEM image, the position of the tip of the needle in the SIM image or SEM image, the position of a foreign object at the tip of the needle 18 in the SIM image or SEM image, and the position of the columnar portion 44 in the SIM image or SEM image. The determination unit 304 determines, as an example, the coordinates of the object in the determination image as the position of the object included in the determination image. The tip of the needle 18 may have a sharpened conical shape, a sharpened cylindrical shape, or a sharpened prismatic shape. Different learning models for the tip shape of the needle 18 can be used depending on the tip shape of the needle 18. This allows needles 18 with various tip shapes to be used in the charged particle beam device 10. The learning model also includes a learning model for the shape of the needle 18 whose tip shape has changed with use, and different models can be used depending on the usage status of the needle 18. Different models can be used depending on the change in tip shape due to use. This means that different learning models can be used and changed depending on the change in tip shape due to use. This allows one needle 18 to be used continuously for a long period of time in one charged particle beam device 10. This reduces the frequency of needle 18 replacement, thereby reducing the number of maintenance times for the charged particle beam device 10. This allows the operating time of the charged particle beam device 10 to be extended.

[0049] The image processing computer 30 may acquire the trained machine learning model from, for example, an external database. In this case, the control unit 300 does not need to include the training data acquisition unit 301 and the training unit 302.

[0050] Below, the automatic micro-sampling (MS) operation performed by the control computer 22, that is, the operation of automatically transferring the sample piece Q formed by processing the sample S with a charged particle beam (focused ion beam) to the sample piece holder P, will be explained in order, broadly divided into an initial setting process, a sample piece pick-up process, a sample piece mounting process, and a needle trimming process.

[0051] (Initial Setting Process) FIG. 7 is a diagram showing an example of an initial setting process according to this embodiment.

[0052] Step S10: The control computer 22 sets the mode and processing conditions. The mode setting is the setting of whether or not to enable the posture control mode (described later) in response to an input from the operator at the start of the automatic sequence. The processing conditions setting is the setting of the processing position, dimensions, number of sample pieces Q, etc.

[0053] Step S20: The control computer 22 registers the position of the columnar portion 44. Here, the control computer 22 transmits to the image processing computer 30 a SIM image or an SEM image that includes the columnar portion 44 as an object.

[0054] In this embodiment, the absorbed current image data including the object is a set of a SIM image of the object and a SEM image of the object. That is, the SIM image and SEM image including the object are a set of a SIM image of the object viewed from an inclined direction at a predetermined angle with respect to the vertical direction of the sample stage 12, and a SEM image of the object viewed from the vertical direction of the sample stage 12.

[0055] 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 based on the machine learning model M. The determination unit 304 outputs position information indicating the determined position of the columnar portion 44 to the control computer 22.

[0056] Here, the determination unit 304 determines the two-dimensional coordinates of the position of the object on the sample stage 12 from a SIM image of the object viewed from a tilted direction tilted at a predetermined angle with respect 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 a plane perpendicular to the tilted direction from a SEM image of the object viewed from a tilted direction tilted at a predetermined angle with respect to the vertical direction of the sample stage 12. The determination unit 304 determines the position of the object as three-dimensional coordinate values ​​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.

[0057] The determination unit 304 uses direction information, which is information about the directions in which the electron beam irradiation optical system 15 and the focused ion beam irradiation optical system 14 are disposed in the charged particle beam device 10 and the angle between them, to calculate the three-dimensional coordinate values. The determination unit 304 either stores the direction information in advance in the storage unit 305 and reads it out, or obtains it from the control computer 22. Here, in step S20, the target object is the columnar portion 44. In the following steps, the process by which the determination unit 304 determines the position of the target object is similar.

[0058] 8 to 12, the columnar portion 44 and the training image of the columnar portion 44 used to generate the machine learning model M will be described. FIGS. 8 and 9 are diagrams showing an example of the columnar portion 44 according to this embodiment. The columnar portion A0 shown in FIGS. 8 and 9 is an example of the designed 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 pillar A01 with a stepped structure is adhered to a base A02.

[0059] FIG. 10 is a diagram showing an example of a training image of the columnar portion 44 according to this embodiment. Training images X11, X12, and X13 are used to learn the position of the columnar portion 44. In training images X11, X12, and X13, information indicating the position of the columnar portion is shown as a circle. In training images X11, X12, and X13, the shapes of pillars A11, A21, and A31 are different from each other. On the other hand, the shapes of bases A12, A22, and A32 are the same in training images X11, X12, and X13.

[0060] Note that the training images X11, X12, and X13 are, for example, training images for determining the position of the columnar portion 44 included in an SIM image or an SEM image when the columnar portion 44 is viewed from the horizontal direction of the sample stage 12. In Fig. 2, 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, but 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 training images X11, X12, and X13 are training images for determining the position of the columnar portion 44 in that case.

[0061] 11 is a diagram showing an example of a columnar portion 44 according to this embodiment in which the pillars do not have a stepped structure. A columnar portion A4 shown in FIG. 11 is a side view of an example of a designed structure of the columnar portion 44 in which the pillars do not have a stepped structure.

[0062] 12 is a diagram showing an example of a training image of a columnar portion 44 in which the pillar according to this embodiment does not have a stepped structure. Training images X21, X22, and X23 are, as an example, training images for determining the position of the columnar portion 44 included in an SEM image when the columnar portion 44 is viewed from the vertical direction of the sample stage 12.

[0063] The shapes of pillars A51, A61, and A71 are different in training images X21, X22, and X23, respectively. On the other hand, the shapes of bases A52, A62, and A72 are the same in training images X21, X22, and X23.

[0064] The machine learning model M is generated based on machine learning using training images that include the bases of the columnar portions 44, and therefore, for example, the shape of the bases is learned as a feature in the machine learning model M. Therefore, even if the pillars have different shapes, the accuracy of determining the columnar portions is improved in the charged particle beam device 10. It is preferable that the target objects in the training images include parts with the same shape among the target objects in multiple training images.

[0065] Returning to FIG. 7, the description of the initial setting process continues.

[0066] 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 .

[0067] The training image of the columnar portion 44 preferably includes images of the columnar portions of the columnar portion 44 located at both ends of the specimen stage 43. Based on the machine learning model M generated using training data including this training image, the image processing computer 30 detects the columnar portions of the columnar portion 44 at both ends of the specimen stage 43, distinguishing them from the other columnar portions. The control computer 22 may calculate the inclination of the specimen holder P from the detected positions of the columnar portions at both ends. The control computer 22 may correct the coordinate values ​​of the position of the target object based on the calculated inclination.

[0068] Step S30: The control computer 22 controls the focused ion beam irradiation optical system 14 to process the sample S.

[0069] 13 is a diagram showing an example of a sample piece pick-up process according to this embodiment. Here, picking up refers to separating and extracting the sample piece Q from the sample S by processing with a focused ion beam or by using a needle.

[0070] Step S40: The control computer 22 adjusts the position of the sample. Here, the control computer 22 moves the sample stage 12 using the stage driving mechanism 13 to bring the target sample piece Q into 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 sample piece Q. After moving the sample stage 12, the control computer 22 aligns the position of the sample piece Q.

[0071] Step S50: The control computer 22 executes the movement of the needle 18.

[0072] 14, a process for moving the needle 18 executed by the control computer 22 will be described. Fig. 14 is a diagram showing an example of the process for moving the needle 18 according to this embodiment. Steps S510 to S540 in Fig. 14 correspond to step S50 in Fig. 13.

[0073] Step S510: The control computer 22 executes needle movement (coarse adjustment) by moving the needle 18 using the needle drive mechanism 19.

[0074] Step S520: The control computer 22 detects the tip of the needle 18. Here, the control computer 22 transmits to the image processing computer 30 absorbed current image data that includes the needle 18 as the target.

[0075] The determination image acquisition unit 303 acquires a SIM image and an SEM image as determination images from the image processing computer 30. The determination unit 304 determines, as the position of the object, the position of the needle 18 included in the determination image acquired by the determination image acquisition unit 303, based on 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.

[0076] Next, the control computer 22 executes needle movement (fine adjustment) by moving the needle 18 using the needle drive mechanism 19 based on the position information indicating the position of the needle 18 determined by the image processing computer 30 .

[0077] 15 to 18, the needle 18 and a learning image of the needle 18 used to generate the machine learning model M will be described. Fig. 15 is a diagram showing an example of SEM image data including the tip of the needle 18 according to this embodiment. Fig. 16 is a diagram showing an example of SIM image data including the tip of the needle 18 according to this embodiment.

[0078] Fig. 17 is a diagram showing an example of the tip of the needle 18 according to this embodiment. Fig. 17 shows a needle B1 as an example of the needle 18 when viewed from an inclined direction that is inclined at a predetermined angle with respect to the vertical direction of the sample stage 12.

[0079] 18 is a diagram showing an example of a training image of the needle 18 according to this embodiment. Training images Y31, Y32, and Y33 are used to learn the position of the tip of the needle 18. In training images Y31, Y32, and Y33, information indicating the position of the tip of the needle 18 is shown as a circle. The thickness of the needle tip is different in training images Y31, Y32, and Y33. On the other hand, the shape of the needle tip is the same in training images Y31, Y32, and Y33.

[0080] The actual thickness of the tip of the needle 18 changes due to cleaning. The machine learning model M is generated based on machine learning using training images that include the tip of the needle 18, and therefore the shape of the tip of the needle, for example, is learned as a feature in the machine learning model M. Therefore, in the charged particle beam device 10, the accuracy of determining the tip of the needle is improved even when the thickness of the tip of the needle varies.

[0081] Returning to FIG. 14, the description of the movement process of the needle 18 will be continued.

[0082] Step S530: The control computer 22 detects the pick-up position of the sample piece Q. Here, the control computer 22 transmits to the image processing computer 30 an SIM image or an SEM image including the sample piece Q as the object.

[0083] Here, the sample piece Q and the learning image of the sample piece Q used to generate the machine learning model M will be described with reference to FIGS. 19 and 20. FIG.

[0084] 19 is a diagram showing an example of SIM image data including the sample piece Q according to this embodiment. In Fig. 19, a sample piece Q71 is shown as an example of the sample piece Q, along with a circle indicating the pickup position.

[0085] 20 is a diagram showing an example of a training image of the sample piece Q according to this embodiment. Training image Z11, training image Z12, and training image Z13 are used to learn the position of the tip of the sample piece Q. In training image Z11, training image Z12, and training image Z13, information indicating the pick-up position of the sample piece Q is shown as a circle. The sizes and surface shapes of the sample pieces are different in training image Z11, training image Z12, and training image Z13. On the other hand, the shapes of the sample pieces at the pick-up positions are the same in training image Z11, training image Z12, and training image Z13.

[0086] The shape of the surface of an actual sample piece differs from one individual to another. The machine learning model M is generated based on machine learning using a training image that includes the pickup position of the sample piece Q. Therefore, in the machine learning model M, for example, the shape of the pickup position of the sample piece Q is learned as a feature. Therefore, in the charged particle beam device 10, even if the surface shape of the sample piece differs, the accuracy of determining the pickup position of the sample piece Q is improved.

[0087] Returning to FIG. 14, the description of the movement process of the needle 18 will be continued.

[0088] Step S540: The control computer 22 moves the needle 18 to the detected pick-up position.

[0089] With this, the control computer 22 ends the process of moving the needle 18 .

[0090] Returning to FIG. 13, the description of the sample piece pick-up step will be continued.

[0091] Step S60: The control computer 22 connects the needle 18 and the sample piece Q. Here, the control computer 22 makes the connection using a deposition film.

[0092] Step S70: The control computer 22 processes and separates the sample S and the sample piece Q. Here, Fig. 21 shows the processing and separation state, and is a diagram showing the cutting processing position T1 of the support portion Qa of the sample S and the sample piece Q in the SIM image data according to an embodiment of the present invention.

[0093] In this embodiment, the sample piece pick-up step and the sample piece mounting step may also be performed on a sample piece Q0 that has been separately prepared and processed in advance. In this case, the pick-up position of the sample piece Q0 may be specified and input to the control computer 22, and the positions of the sample piece transfer means (needle 18) and the sample piece Q0 may be adjusted, and then the cutting processing position T1 in Figure 21 may be determined by machine learning. In this case, the machine learning uses, as the first image, an image showing the position (cutting processing position) to which the sample piece transfer means is to approach the sample piece in the sample extraction step of extracting the sample piece.

[0094] In this case, the sample piece Q0 can be extracted and separated even if processing size and shape information indicating the processing size and shape of the sample piece Q0 has not been input to the control computer 22. After the sample piece Q0 is extracted, the subsequent sample piece mounting process may be performed in the same manner.

[0095] 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 and moves the needle 18 to retract it, similar to the process of moving the needle 18 in step S50.

[0096] Step S90: The control computer 22 moves the sample stage 12. Here, the control computer 22 causes the stage driving mechanism 13 to move the sample stage 12 so that the specific columnar portion 44 registered in the above-mentioned step S20 is within the observation field of view area of ​​the charged particle beam.

[0097] 22 is a diagram showing an example of a sample piece mounting step according to this embodiment. The sample piece mounting step is a step of transferring the extracted sample piece Q to a sample piece holder P.

[0098] Step S100: The control computer 22 determines the relocation position of the sample piece Q. Here, the control computer 22 determines the specific columnar portion 44 registered in the above-mentioned step S20 as the relocation position.

[0099] 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 step S520 described above.

[0100] Step S120: The control computer 22 moves the needle 18. Here, the control computer 22 moves the needle 18 by the needle drive mechanism 19 to the relocation position of the sample 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 sample piece Q.

[0101] Step S130: The control computer 22 connects the sample piece Q connected to the needle 18 to the columnar portion 44.

[0102] Step S140: The control computer 22 separates the needle 18 from the sample piece Q. Here, the control computer 22 performs the separation by cutting the deposition film DM2 connecting the needle 18 and the sample piece Q.

[0103] Step S150: The control computer 22 retracts the needle 18. Here, the control computer 22 causes the needle drive mechanism 19 to move the needle 18 away from the sample piece Q by a predetermined distance.

[0104] Step S160: The control computer 22 determines whether or not to perform the next sampling. Here, performing the next sampling means continuing sampling from a different location on the same sample S. The number of samples to be sampled is set in advance in step S10, so the control computer 22 checks this data and determines whether or not to perform the next sampling.

[0105] If it is determined that the next sampling should be performed (No), the control computer 22 performs the needle trimming step S230 shown in FIG. 23 , then proceeds to step S50, and continues the subsequent steps to perform the sampling operation as described above. In this example, step S160 includes the needle trimming step S230. The needle trimming step S230 may be performed between step S160 and step S50.

[0106] On the other hand, if it is determined that the next sampling is not to be performed (Yes), the control computer 22 ends the series of automatic MS flows.

[0107] Next, the needle trimming step (step S230) will be described with reference to Fig. 23. Fig. 23 is a diagram showing an example of the needle trimming step according to the embodiment.

[0108] (Step S230: Needle Trimming Step) The control computer 22 executes the needle trimming step S230.

[0109] Step S231: After sampling in the automatic sample sampling, that is, after detaching the sample piece Q separated and extracted from the sample S by the needle 18 from the needle 18, the control computer 22 performs needle cleaning by trimming the needle 18. This allows the control computer 22 to repeatedly use the needle 18 when separating and extracting the sample piece Q from the sample S. The control computer 22 removes any attachments such as the deposition film DM2 and sample piece residue adhering to the needle 18 by etching using a focused ion beam. The attachments such as the deposition film DM2 and sample piece residue adhering to the needle 18 can be referred to as foreign matter.

[0110] Step S232: The control computer 22 moves the needle 18 and the stage 13 to a location where there is no structure behind the needle 18, and stops them.

[0111] Step S233: The control computer 22 acquires image data including the needle 18 by irradiating it with the focused ion beam. The acquired image including the needle 18 is sent to the image processing computer 30. The determination image acquisition unit 303 acquires the image from the image processing computer 30 as a determination image.

[0112] Step S234: The determination unit 304 determines whether the tip of the needle 18 included in the determination image acquired by the determination image acquisition unit 303 is detected, based on the machine learning model M. If it is determined that the tip of the needle 18 is detected (Yes), the determination unit 304 outputs position information indicating the determined position of the needle 18 to the control computer 22, and proceeds to step S235. If it is determined that the tip of the needle 18 is not detected (No), the process proceeds to step S232, and the subsequent steps are executed as described above.

[0113] 24 and 25, an example of a training image of the needle 18 used to generate the machine learning model M will be described. Note that the training images Y31-Y33 shown in FIG. 18 described above can also be used.

[0114] 24 is a diagram showing an example of a training image of a needle according to this embodiment. Training image Y41, training image Y42, and training image Y43 are used to learn the position of the tip of the needle 18. In training image Y41, training image Y42, and training image Y43, information indicating the position of the tip of the needle 18 is shown as a circle. The thickness of the needle tip is different in training image Y41, training image Y42, and training image Y43. On the other hand, the shape of the needle tip is the same in training image Y41, training image Y42, and training image Y43.

[0115] The actual thickness of the tip of the needle 18 changes due to cleaning. FIG. 25 is a diagram showing an example of a training image of a needle whose tip thickness has changed due to cleaning according to this embodiment. Training images Y51, Y52, and Y53 are examples of training images of needles 18 whose tip thickness has changed due to cleaning, and are used to learn the position of the tip of the needle 18. In training images Y51, Y52, and Y53, information indicating the position of the tip of the needle 18 is shown as a circle. Training images Y51, Y52, and Y53 show cases where the thickness of the tip of the needle shown in training images Y41, Y42, and Y43 has changed due to cleaning. Note that the tip of the needle 18 may also become thicker if the needle 18 is accidentally cut near the base during use. It is preferable to create the learning images Y51, Y52, and Y53 taking into consideration the case where the needle 18 is accidentally cut off.

[0116] Returning to FIG. 23, step S235 will be described.

[0117] Step S235: The control computer 22 moves the needle 18 and the stage 13 to move the tip of the needle 18 to the center of the field of view.

[0118] Step S236: The control computer 22 moves the tip of the needle 18 to the center of the field of view, and then stops the movement of the needle 18.

[0119] Step S237: The control computer 22 obtains image data including the tip of the needle 18 by irradiating the focused ion beam. The obtained image including the needle 18 is sent to the image processing computer 30.

[0120] Step S238: The control computer 22 determines whether cleaning of the needle 18 is necessary. The determination image acquisition unit 303 acquires an image as a determination image from the image processing computer 30. The determination unit 304 determines whether foreign matter is attached to the tip of the needle 18 based on the machine learning model M. If it is determined that foreign matter is not attached to the tip of the needle 18, it determines that cleaning of the needle 18 is unnecessary (No), and proceeds to step S239. The machine learning model M used here has learned the learning images of the needle 18 described in FIGS. 24 and 25 , and therefore can accurately determine the shape of the needle 18, and can accurately determine whether foreign matter is attached to the tip of the needle 18.

[0121] If it is determined that foreign matter is attached to the tip of the needle 18, it is determined that cleaning of the needle 18 is necessary (Yes), and the process proceeds to step S240. At this time, the position of the foreign matter attached to the tip of the needle 18 contained in the determination image acquired by the determination image acquisition unit 303 is determined as the position of the target object. The determination unit 304 outputs position information indicating the determined position of the needle 18 to the control computer 22. The machine learning model M used here includes a learning model for determining a foreign matter region and a learning model for determining whether needle cleaning is necessary, which will be described below.

[0122] Here, with reference to FIGS. 26 , 27 , 28 , 29 , and 30 , an example of a learning image of a needle 18 used to generate a machine learning model M used to determine whether cleaning is necessary will be described. FIGS. 26 to 29 are diagrams showing an example of a learning model for determining a foreign matter region. FIG. 26 is a diagram showing an example of an original image of a needle with foreign matter attached. FIG. 27 is a diagram showing an example of a teacher image showing a foreign matter region in the original image of FIG. 26 . FIG. 28 is a diagram showing an example of an original image in which the contrast, angle, magnification, position, etc. of the needle have been changed. FIG. 29 is a diagram showing an example of an original image in which foreign matter has attached to the tip of a needle whose tip thickness has changed due to cleaning, and one set of learning data for that teacher image. FIG. 30 is a diagram showing an example of a learning model for determining whether needle cleaning is necessary.

[0123] As shown in Figure 26, original images Y61 to Y66 of the needle 18 have a foreign substance FB attached to the tip portion of the needle 18. Figure 27 shows teacher images Y61T to Y66T that indicate the region of the foreign substance FB in the original images Y61 to Y66. To generate the machine learning model M, the original image Y61 and the teacher image Y61T are used as pairs of training data. Similarly, the original image Y62 and the teacher image Y62T, the original image Y63 and the teacher image Y63T, the original image Y64 and the teacher image Y64T, the original image Y65 and the teacher image Y65T, and the original image Y66 and the teacher image Y66T are used as pairs of training data.

[0124] The learning data used to generate the machine learning model M consists of an original image and a teacher image. The teacher image contains information indicating only the foreign substance portion of the original image. The teacher image is created, for example, by specifying which part of the original image is the foreign substance region. By inputting multiple pieces of learning data into the machine learning model M, it becomes possible to determine the foreign substance region from the original image of the needle with the foreign substance attached. Note that it is also possible to add learning data to the machine learning model M later based on image data of the tip of the needle 18 acquired during use of the charged particle beam device 10.

[0125] 28 shows original images Y67-Y70 in which the contrast, angle, magnification, position, etc. of the needle 18 are changed. As shown in the example of FIG. 28, it is preferable to use, as original images used for image training data, images in which the shape of the tip of the needle 18, the manner in which the foreign matter is attached, contrast, magnification, angle and position of the needle 18, etc. are changed. Creating a training model that incorporates images under various conditions enables highly robust determination of foreign matter regions.

[0126] 29 shows an original image Y71 in which a foreign substance FB is attached to the tip of a needle 18 whose tip thickness has changed due to cleaning, and its corresponding teacher image Y71T. Even if the tip shape of the needle 18 loses its sharpness due to repeated use, in order to accurately determine the area of ​​foreign matter, it is advisable to also prepare a separate machine learning model for determining the area of ​​foreign matter, which is composed of a learning set of an original image (Y71) of the needle tip in a scraped state and a teacher image (Y71T) of foreign matter attached thereto. By using different machine learning models depending on the frequency of needle cleaning, the area of ​​foreign matter can be reliably determined.

[0127] An example of a machine learning model for determining whether needle cleaning is necessary is shown in Fig. 30. The learning model for determining whether needle cleaning is necessary includes an image Y81 showing an example of a needle 18 that does not require cleaning and an image Y82 showing an example of a needle 18 that requires cleaning. The determination of whether needle cleaning is necessary may use the machine learning model for determining foreign matter regions (Figs. 26 to 29) or the machine learning model for determining needle cleaning (Fig. 30).

[0128] If the area (number of pixels) of the region determined to be a foreign substance in step S238 is smaller than a certain value, it can be determined that there is "no effect on microsampling" and the cleaning process (steps S240 and S241) described below can be skipped. This determination can be made by applying the results of the foreign substance region determination model (Figures 26, 27, etc.).

[0129] Returning to FIG. 23, step S239 will be described.

[0130] Step S239: The control of the control computer 22 proceeds to step S50 for processing the next sample piece Q.

[0131] Step S240: The control computer 22 determines a cleaning area for the needle 18. The control computer 22 sets a processing frame (also called a processing area) for performing etching using a focused ion beam, based on position information indicating the position of the foreign matter adhering to the tip of the needle 18 determined by the image processing computer 30. Setting of the processing frame will be described later.

[0132] Step S241: The control computer 22 etches the range of the set processing frame with a focused ion beam to remove foreign matter such as a deposition film or residue of a sample piece adhering to the needle 18, and then shapes the tip of the needle 18 into a desired shape with the focused ion beam. Thereafter, the control of the control computer 22 proceeds to step S237, and the subsequent steps are executed.

[0133] In this way, the control computer 22 uses the machine learning model M that has learned information including the image of the needle, and controls the charged particle beam irradiation optical system so as to shape the needle 18 based on the judgment of the machine learning model M. In this way, the control computer 22 can remove foreign matter such as deposits, such as a deposition film or residue of a sample piece, adhering to the needle 18, and can shape the tip of the needle 18 into a desired shape using the focused ion beam.

[0134] If an abnormality occurs in the foreign body region determination process in the image processing computer 30, the control computer 22 initializes the position coordinates of the needle 18, moves the needle 18 to its initial position, and then moves the needle 18 to a location where there are no structures in the background of the needle 18. Furthermore, if an abnormality occurs in the foreign body region determination process in the image processing computer 30 even after the position coordinates of the needle 18 have been initialized, the control computer 22 determines that an abnormality such as deformation has occurred in the shape of the needle 18, displays a warning message on the screen, and terminates automatic sample sampling. Alternatively, the control computer 22 executes an automatic needle 18 replacement sequence.

[0135] The control computer 22 may perform the needle trimming process (step S230) each time automatic sample sampling is performed. By periodically performing the needle trimming process (step S230), the automatic sample sampling process can be stabilized. In particular, by removing deposits such as the deposition film DM2 and residue of the sample piece Q adhering to the tip of the needle 18 adjacent to the sample piece Q and exposing the tip of the needle 18, the fixing strength between the needle 18 and the sample piece Q can be maintained. By performing the needle trimming process (step S230), the needle 18 can be repeatedly used to sample the sample piece Q without being replaced, and therefore multiple sample pieces Q can be continuously sampled using the same needle 18.

[0136] The timing of performing the needle trimming step (S230) is not limited to when automatic sample sampling is being performed, but can be performed at any timing, such as when the needle 18 is first replaced.

[0137] Next, the setting of the processing frame will be described.

[0138] (Setting of Processing Frame by Artificial Intelligence (AI)) As described in the needle trimming process (S230), the image processing computer 30 uses image data (step S237) generated by irradiation with a focused ion beam to perform image recognition (step S238) of the position of the tip of the needle 18, and then determines a foreign matter area attached to the needle 18 (step S240). The foreign matter area determined by the image processing computer 30 is transmitted to the control computer 22, which sets a processing frame (processing area) for the focused ion beam corresponding to the foreign matter area and performs sharpening of the tip of the needle 18 (step S241). Here, sharpening can be considered to include a removal process of removing foreign matter from the tip of the needle 18 and a shaping process of shaping the tip of the needle 18 into a desired shape.

[0139] The processing frame of a focused ion beam will be described with reference to Figs. 31 to 34. Fig. 31 is a diagram for explaining an example of the processing frame according to a comparative example. Fig. 32 is a diagram for explaining the problems with the processing frame according to a comparative example. Fig. 33 is a diagram for explaining an example of the processing frame according to an example. Fig. 34 is a diagram for explaining an example of setting the processing frame according to an example.

[0140] 31 shows the tip of the needle 18 in which a processing frame 40a according to a comparative example is set. The processing frame 40a is a rectangular processing frame that assumes an ideal tip position C by linearly approximating the area from the tip of the needle 18 to the base end side, etc. In this example, processing frames 40a are set on both the upper and lower sides of the needle 18. By performing etching within the range of the processing frame 40a (the range inside the frame) using a focused ion beam, foreign matter FB adhering to the upper and lower sides of the needle 18 can be removed.

[0141] 32 shows a case where the foreign matter FB is attached to the tip of the needle 18. In this example, the foreign matter FB is located between the processing frames 40a set on the upper and lower sides of the needle 18. Therefore, even if etching is performed using a focused ion beam, the foreign matter FB is not located within the range of the processing frame 40a (the range inside the frame), so there is a problem that the foreign matter FB cannot be removed. In other words, the foreign matter FB attached to the tip of the needle 18 cannot be removed.

[0142] FIG. 33 shows an example of a processing frame 40 according to the embodiment. As shown in FIG. 33, in this example, the processing frame 40 is a rectangular processing frame set to surround the foreign matter FB. Therefore, when etching is performed using a focused ion beam, the foreign matter FB is located within the range of the processing frame 40 (the range inside the frame), so that the foreign matter FB can be removed, unlike the case of the processing frame 40a described in FIG. 32. In other words, the foreign matter FB attached to the tip of the needle 18 can be removed.

[0143] 34 shows examples of setting a processing frame according to the embodiment, where (A) shows an example of an image of a needle 18 with a foreign matter FB attached to its tip, (B) shows an example in which a processing frame 40 having the same shape as the foreign matter FB is set around the foreign matter FB, and (C) shows an example in which a rectangular processing frame 40 is set around the foreign matter FB so as to surround the foreign matter FB. In this way, the shape of the processing frame 40 can be set to any shape, and can be selected to match the shape of the foreign matter.

[0144] The shape of the processing frame 40 set by the control computer 22 is different from the rectangular processing frame 40a shown in Figures 31 and 32, which assumes an ideal tip position C by linearly approximating the area from the tip to the base end of the needle 18, and is a processing frame 40 set in an area where foreign matter adheres, as shown in Figures 33 and 34.

[0145] Therefore, the processing frame 40 can be installed even when foreign matter FB has adhered to the gap between the ideal tip position C and the actual tip of the needle 18. Therefore, it is possible to remove foreign matter FB that has adhered to the gap between the ideal tip position C and the actual tip of the needle 18. By performing this foreign matter removal processing and sharpening processing on the needle 18, the tip of the needle 18 can be restored to a state in which the main body is exposed and free of foreign matter. This allows the needle 18 to be processed into a shape optimal for transferring the sample piece Q.

[0146] In addition, when the image processing computer 30 determines, for example, in step S238, that there is no area corresponding to the foreign matter FB in the image of the needle 18, the control computer 22 does not set the processing frame 40 using the focused ion beam, and the needle cleaning process there (S240, S241) is skipped.

[0147] Furthermore, if the image processing computer 30 cannot identify the shape of the needle 18 in the image of the needle 18 in step S238, for example, and determines that the needle 18 is deformed, the control computer 22 does not set the focused ion beam processing frame 40 and skips the needle cleaning process (S240, S241). Alternatively, an automatic needle replacement process may be performed thereafter, or the needle 18 may be determined to be deformed and reshaped to correct the deformation. Reshaping the deformed needle 18 results in a needle with an optimal shape for transferring a sample piece. Figure 35 is a diagram illustrating the reshaping of the needle 18. As shown in Figure 35, the initial needle 18a may be deformed like the needle 18b after use or after significant wear due to some other cause. In other words, the tip of the initial needle 18a is sharply pointed like the corner of a triangle, while the tip of the deformed needle 18b has a rectangular shape. Therefore, the shape of the needle 18a is recognized by artificial intelligence (AI), and the control computer 22 places a processing frame 40 (two processing frames 40 in this example) on the needle 18b and reshapes the needle by sharpening. That is, based on the judgment of the machine learning model, the control computer 22 irradiates a charged particle beam from the charged particle beam irradiation optical system 14 and shapes the needle 18b based on the processing frame 40. By shaping the tip of the needle 18b, for example, a needle 18c having a sharpened tip can be obtained. This allows for the needle 18c to have an optimal shape for transferring a sample piece. While FIG. 35 illustrates a case where the tip of the needle is sharply pointed, such as a triangular corner, it is also possible to set the processing frame 40 so that the tip of the needle has a prismatic shape. Even if the tip of the needle is prismatic, it can be said to have an optimal shape for transferring a sample piece.

[0148] The image processing computer 30 also recognizes the size of the foreign matter FB adhering to the needle 18 and transmits the determination result of the size of the foreign matter FB to the control computer 22. Based on the foreign matter size information received from the image processing computer 30, the control computer 22 controls the focused ion beam irradiation optical system 14, which is the focused ion beam irradiation unit, and changes the beam conditions of the focused ion beam irradiated to the foreign matter FB. In other words, the current amount of the focused ion beam irradiated to the foreign matter FB may be changed. The processing time can be shortened by removing large foreign matter FB with a large amount of focused ion beam. The foreign matter FB can be accurately removed by removing small foreign matter FB with a small amount of focused ion beam with small aberration.

[0149] When the control computer 22 places the processing frame 40 in an area that the image processing computer 30 has determined to be the area of ​​the foreign matter FB, the control computer 22 may use the coordinate information of the area of ​​the foreign matter FB, or may place the processing frame 40 based on an image of the area that has been determined to be the area of ​​the foreign matter FB.

[0150] The control computer 22 rotates the needle 18 around the central axis using the rotation mechanism of the needle drive mechanism 19, and performs etching in the same manner at a plurality of different specific rotation positions to shape the needle 18 into a desired shape. Note that the operator can select whether or not to perform etching at a plurality of different specific rotation positions of the needle 18 using the rotation mechanism of the needle drive mechanism 19.

[0151] In addition to the processing frame 40 set by the control computer 22 for the area determined by the image processing computer 30 to be a foreign substance FB, a conventional method of detecting the edge of the needle 18 may also be used.

[0152] If the area of ​​the region determined by the image processing computer 30 to be the foreign matter FB is smaller than a specified value, the needle cleaning process (S240, S241) can be skipped.

[0153] Furthermore, the operator can select whether or not to carry out cleaning processing on the area that the image processing computer 30 has determined to be a foreign substance FB, depending on the type and importance of the sample to be sampled next.

[0154] Since the shape of the needle 18 gradually changes as it goes through the process of adhering and cutting the sample, a learning model can be selected depending on the number of times it is used (see FIG. 29).

[0155] The end of the needle cleaning process may be determined based on the processing time, or may be determined again by artificial intelligence (AI) using the machine learning model M. When the determination is made by artificial intelligence (AI), the needle trimming process (step S230) is terminated if the area of ​​the foreign matter FB is not determined or if the area determined as the area of ​​the foreign matter FB is smaller than a specified size. Alternatively, a learning model of an ideally shaped needle 18 with no foreign matter FB attached may be prepared for the end determination (see Y81 in FIG. 30). Furthermore, the determination method using the artificial intelligence (AI) and the determination method using a learning model of an ideally shaped needle 18 with no foreign matter FB attached may be used in combination.

[0156] When the needle 18 with the foreign matter FB attached thereto is successfully cleaned, the image data may be imported into the image processing computer 30 and used as training data for self-learning. In this case, whether sampling with the needle 18 after cleaning was successful is added to the criteria for whether the data can be used as training data.

[0157] Furthermore, a learning model including self-learned training data can also be used as a learning model for another device.

[0158] By matching the tip shape of the needle 18 to a predetermined ideal shape, the computer 22 can easily recognize the needle 18 by pattern matching when driving the needle 18 in three-dimensional space, and can accurately detect the position of the needle 18 in three-dimensional space.

[0159] (Modification) In the above embodiment, the initial setting process, the sample piece pick-up process, the sample piece mounting process, and the needle trimming process are controlled using the machine learning model M. However, the present invention is not limited to this. If the machine learning model M is used to control at least the needle trimming process, a charged particle beam device that can remove the foreign matter FB adhering to the tip of the needle 18 can be provided.

[0160] In the present embodiment, an example has been described in which the training data is a set of a training image and information indicating the position of an object in the training image, but the present invention is not limited to this. In addition to the training image, the training data may also include parameter information that indicates the type of sample, scan parameters (such as the acceleration voltages 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 since cleaning, whether or not foreign matter is attached to the tip of the needle 18, and so on.

[0161] In this case, the machine learning model M is generated by executing machine learning based on the training image and parameter information. The determination unit 304 also acquires the parameter information in addition to the image data of the SIM image or 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 machine learning model M.

[0162] Furthermore, the parameter information may further include the above-mentioned directional information. When the learning data includes directional information, the machine learning model M is generated by learning the relationship between the object and the direction in which the object is viewed (the direction relative to the specimen stage 12), so the determination unit 304 does not need to use the directional information to determine the position of the object.

[0163] As described above, the computer (in this embodiment, the control computer 22) controls the position of the second object (in this embodiment, the columnar portion 44, the needle 18, and the sample piece Q) based on the result of the image processing computer 30 determining the position of the second object (in this embodiment, the columnar portion 44, the needle 18, and the sample piece Q) based on the machine learning model (in this embodiment, the machine learning model M) and the second information including the second image (in this embodiment, an SIM image or an SEM image of the columnar portion 44, the needle 18, and the sample piece Q). The image processing computer 30 and the control computer 22 may be provided integrally in the charged particle beam device 10.

[0164] The invention made by the inventor has been specifically described above based on examples, but it goes without saying that the present invention is not limited to the above-described embodiments and examples, and various modifications are possible.

[0165] 10: charged particle beam device, 18: needle, 22: control computer, 30: image processing computer, M: machine learning model, FB: foreign substance

Claims

1. a charged particle beam irradiation optical system for irradiating a charged particle beam; a sample stage on which a sample is placed and moved; a specimen transfer means including a needle for holding and transporting a specimen to be separated and extracted from the specimen, and a needle drive mechanism for driving the needle; a holder fixing table for holding a specimen holder to which the specimen is transferred; a machine learning model that has learned information including an image of a foreign substance attached to the needle and an image of a foreign substance portion in the image; a computer that determines a region of foreign matter adhering to the needle based on the judgment of the machine learning model, irradiates the region with the charged particle beam, and controls the charged particle beam irradiation optical system to process the foreign matter; A charged particle beam device comprising:

2. (delete)

3. (delete)

4. (delete)

5. The image of the needle to be trained by the machine learning model is An image showing the shape of the needle is included.

10. The charged particle beam device according to claim 1.

6. The computer If it is determined based on the judgment of the machine learning model that there is no region of foreign matter attached to the needle, the irradiation of the charged particle beam is skipped.

10. The charged particle beam device according to claim 1.

7. The computer If the area of ​​the region determined to be a region of foreign matter adhering to the needle based on the judgment of the machine learning model is smaller than a specified value, the irradiation of the charged particle beam is skipped.

7. The charged particle beam device according to claim 6.

8. The computer changing beam conditions of the charged particle beam based on an area of ​​a region determined to be a region of foreign matter adhering to the needle based on the judgment of the machine learning model; 10. The charged particle beam device according to claim 1.

9. The computer When the shape of the needle cannot be identified and it is determined that the needle is deformed based on the judgment of the machine learning model, the irradiation of the charged particle beam is skipped or a step of replacing the needle is performed.

10. The charged particle beam device according to claim 1.

10. extracting the specimen from the sample using the needle and transferring it to the specimen holder; moving the needle to an irradiation position of the charged particle beam; irradiating the needle with the charged particle beam to acquire an image; processing the image using the machine learning model to determine a processing area in which foreign matter adhering to the needle is to be removed; and irradiating the processing region with the charged particle beam to remove foreign matter adhering to the needle.

10. The charged particle beam device according to claim 1.

11. (delete)

12. and another machine learning model that has learned information including an image of the needle with a chipped tip and an image of the foreign matter adhering to the needle, and an image of the foreign matter portion of the image, the computer determines a region of foreign matter adhering to the needle based on the determination of the other machine learning model, and controls the charged particle beam irradiation optical system to irradiate the region with the charged particle beam and process the foreign matter.

10. The charged particle beam device according to claim 1.