To accomplish fast automated micro-sampling, provided is a charged particle beam apparatus, which is configured to automatically fabricate a sample piece from a sample, the charged particle beam apparatus including: a charged particle beam irradiation optical system configured to radiate a charged particle beam; a sample stage configured to move the sample that is placed on the sample stage; a sample piece transportation unit configured to hold and convey the sample piece separated and extracted from the sample; a holder fixing base configured to hold a sample piece holder to which the sample piece is transported; and a computer configured to perform position control with respect to a second target, based on a machine learning model in which first information including a first image of a first target is learned, and on second information including a second image, which is obtained by irradiation with the charged particle beam.

A focused ion beam (FIB) is used to mill beam spots into a substrate at a variety of ion beam column settings to form a set of training images that are used to train a convolutional neural network. After the neural network is trained, an ion beam can be adjusted by obtaining spot image which is processed with the neural network. The neural network can provide a magnitude and direction of defocus, aperture position, lens adjustments, or other ion beam or ion beam column settings. In some cases, adjustments are not made by the neural network, but serve to indicate that the ion beam and associated ion column continue to operate stably, and additional adjustment is not required.

To stabilize automated MS, provided is a charged particle beam apparatus, which is configured to automatically fabricate a sample piece from a sample, the charged particle beam apparatus including: a charged particle beam irradiation optical system configured to radiate a charged particle beam; a sample stage configured to move the sample that is placed on the sample stage; a sample piece transportation unit configured to hold and convey the sample piece separated and extracted from the sample; a holder fixing base configured to hold a sample piece holder to which the sample piece is transported; and a computer configured to perform control of a position with respect to a target, based on: a result of second determination about the position, which is executed depending on a result of first determination about the position; and information including an image that is obtained by irradiation with the charged particle beam.

An inspection device includes a charged particle optical system that includes a charged particle beam source emitting a charged particle beam and plural lenses focusing the charged particle beam on a sample, a detector that detects secondary charged particles emitted by an interaction of the charged particle beam and the sample, and a calculation unit that executes auto-focusing at a time a field of view of the charged particle optical system moves over plural inspection spots, the calculation unit irradiates the charged particle beam to the sample under an optical condition that is obtained by introducing astigmatism of a predetermined specification to an optical condition that is for observing a pattern by the charged particle optical system, and executes the auto-focusing using an image formed from a signal outputted by the detector in detecting the secondary charged particles.

Methods and apparatuses for implementing artificial intelligence enabled volume reconstruction are disclosed herein. An example method at least includes acquiring a first plurality of multi-energy images of a surface of a sample, each image of the first plurality of multi-energy images obtained at a different beam energy, where each image of the first plurality of multi-energy images include data from a different depth within the sample, and reconstructing, by an artificial neural network, at least a volume of the sample based on the first plurality of multi-energy images, where a resolution of the reconstruction is greater than a resolution of the first plurality of multi-energy images.

An ion beam irradiation apparatus includes modules for generating an ion beam meeting a processing condition, and a machine learning part that generates a learning algorithm using, as an explanatory variable, a processing condition during new processing and a monitored value that indicates a state of a module during a last processing immediately before the new processing, and a basic operation parameter output part that uses the learning algorithm to output an initial value of a basic operation parameter for controlling an operation of the module.

Methods, systems, and non-transitory computer readable medium are provided for correcting component failures in ion implant semiconductor manufacturing tool. A method includes receiving, from sensors associated with an ion implant tool, current sensor data corresponding to features; performing feature analysis to generate additional features for the current sensor data; providing the additional features as input to a trained machine learning model; obtaining one or more outputs from the trained machine learning model, where the one or more outputs are indicative of a level of confidence of a predicted window; predicting, based on the level of confidence of the predicted window, whether one or more components of the ion implant tool are within a pre-failure window; and responsive to predicting that the one or more components are within the pre-failure window, performing a corrective action associated with the ion implant tool.

A focused ion beam (FIB) is used to mill beam spots into a substrate at a variety of ion beam column settings to form a set of training images that are used to train a convolutional neural network. After the neural network is trained, an ion beam can be adjusted by obtaining spot image which is processed with the neural network. The neural network can provide a magnitude and direction of defocus, aperture position, lens adjustments, or other ion beam or ion beam column settings. In some cases, adjustments are not made by the neural network, but serve to indicate that the ion beam and associated ion column continue to operate stably, and additional adjustment is not required.

The disclosure relates to a method of aligning a charged particle beam apparatus, comprising the steps of providing a charged particle beam apparatus in a first alignment state; using an alignment algorithm, by a processing unit, for effecting an alignment transition from said first alignment state towards a second alignment state of said charged particle beam apparatus; and providing data related to said alignment transition to a modification algorithm for modifying said alignment algorithm in order to effect a modified alignment transition.

An ion beam irradiation apparatus includes modules for generating an ion beam according to a recipe, and a control device. The control device receives the recipe including a processing condition for new processing, reads, from a monitored value storage, a monitored value that indicates a state of a module during a last processing immediately before the new processing, inputs the processing condition and the monitored value to a trained machine learning algorithm and receives, as an output from the trained machine learning algorithm, an initial value for the module, and outputs the initial value to the module to set up the module for generating the ion beam.