Artificial intelligence-enabled preparation end-pointing
AssigneeFEI Company
InventorsThomas Gary Miller, John F. Flanagan, IV, Brian Routh, Jr., Richard Young, Brad Larson, Aditee Shrotre
Life of this patent
Estimating the term…
Abstract
Methods and systems for implementing artificial intelligence enabled preparation end-pointing are disclosed. An example method at least includes obtaining an image of a surface of a sample, the sample including a plurality of features, analyzing the image to determine whether an end point has been reached, the end point based on a feature of interest out of the plurality of features observable in the image, and based on the end point not being reached, removing a layer of material from the surface of the sample.
Claims16
A method implemented by a controller executing code, the method comprising:
- obtaining, by a charged particle beam, an image of a surface of a sample, the sample including a plurality of features;
- analyzing, by a machine learning system, the image to determine a relative position of a milled face of the sample to a feature of interest out of the plurality of features observable in the image, wherein the analyzing of the image includes at least one of:
- determining a relative rotation of the milled face to the feature of interest, and tracking an amount of the relative rotation over a plurality of images obtained of the surface of the sample, and
- determining, by the machine learning system, a first class probability and a second class probability for at least one of the plurality of features, and determining rotation of the sample from the imaged surface based on the first class probability and the second class probability;
- and
- based on the relative position, adjusting milling, by a focused ion beam, of the surface of the sample.
A charged particle microscope system for processing samples, the system comprising:
- an ion column to provide a focused ion beam;
- an electron column to provide an electron beam;
- and
- a controller including code that, when executed, causes the charged particle microscope to:
- obtain, by the electron beam, an image of a surface of a sample, the sample including a plurality of features;
- analyze, by a machine learning system, the image to determine a relative position of a milled face of the sample to a feature of interest out of the plurality of features observable in the image, wherein the code causing the charged particle microscope to analyze the image includes at least one of:
- code that, when executed, causes the charged particle microscope to determine a relative rotation of the milled face to the feature of interest, and to track an amount of the relative rotation over a plurality of images obtained of the surface of the sample;
- and
- code that, when executed, causes the charged particle microscope to determine, by the machine learning system, a first class probability and a second class probability for at least one of the plurality of features, and to determine rotation of the sample from the imaged surface based on the first class probability and the second class probability;
- and
- based on the relative position, adjust milling, by the focused ion beam, of the surface of the sample.
Dependencies are inferred from the claim text.