Hyperdimensional scanning transmission electron microscopy and examinations and related systems, methods, and devices

Patent metadata

Field	Value
Publication number	US-11852598-B2
Application number	US-201917309074-A
Country	US
Kind code	B2
Filing date	Oct 23, 2019
Priority date	Nov 5, 2018
Publication date	Dec 26, 2023
Grant date	Dec 26, 2023

Abstract

A material identification system includes one or more data interfaces configured to receive first sensor data generated by a first sensor responsive to a material sample, and receive second sensor data generated by a second sensor responsive to the material sample. The material identification system also includes one or more processors configured to generate a set of predictions of an identification of the material sample and a corresponding set of certainty information.

First claim

What is claimed is:

1. A material identification system, comprising:
one or more data interfaces configured to:
receive first sensor data generated by a first sensor responsive to a material sample; and
receive second sensor data generated by a second sensor responsive to the material sample; and

one or more processors operably coupled to the one or more data interfaces, the one or more processors configured to apply the first sensor data and the second sensor data to one or more neural networks to:
generate a first preliminary set of predictions of an identification of the material sample and a corresponding first preliminary set of certainty information responsive to the first sensor data;
generate a second preliminary set of predictions of the identification of the material sample and a corresponding second preliminary set of certainty information responsive to the second sensor data; and
narrow the first preliminary set of predictions based on the second preliminary set of predictions, the first preliminary set of certainty information, and the second preliminary second set of certainty information to generate a set of predictions of the identification of the material sample and a corresponding set of certainty information.

2. The material identification system of claim 1 , wherein the first sensor comprises a diffraction sensor including at least one of an x-ray diffraction apparatus, an electron based scattering diffraction apparatus, a selected area electron diffraction apparatus, or a high resolution atomic scale scanning transmission electron microscope.

3. The material identification system of claim 2 , wherein the second sensor comprises a chemistry sensor including at least one of an energy dispersive x-ray spectroscopy apparatus, an atom probe tomography apparatus, a mass spectrometer, and an electron energy loss spectroscopy apparatus.

4. The material identification system of claim 2 , wherein the second sensor comprises an electron imaging sensor.

5. The material identification system of claim 2 , wherein the second sensor comprises a spectroscopy sensor including at least one of an x-ray spectroscopy apparatus and an electron energy loss spectroscopy apparatus.

6. The material identification system of claim 2 , wherein the second sensor comprises another diffraction sensor that is different from the diffraction sensor of the first sensor.

7. The material identification system of claim 1 , wherein the first sensor data comprises diffraction data.

8. The material identification system of claim 7 , wherein the second sensor data comprises at least one of chemistry data, image data, and spectroscopy data.

9. The material identification system of claim 7 , wherein the second sensor data comprises diffraction data that is different from the diffraction data of the first sensor data.

10. The material identification system of claim 1 , wherein the one or more processors are configured to rank the set of predictions from most certain to least certain based on the corresponding set of certainty information and generate a prediction including a highest ranked prediction of the set of predictions to predict the identification of the material sample.

11. The material identification system of claim 1 , wherein the one or more data interfaces is further configured to receive third sensor data generated by a third sensor responsive to the material sample, wherein the one or more processors are further configured to apply the third sensor data to the one or more neural networks to:
generate a third preliminary set of predictions of the identification of the material sample and a corresponding third preliminary set of certainty information responsive to the third sensor data; and
narrow the first preliminary set of predictions based on the third preliminary set of predictions and the third preliminary set of certainty information in addition to the second preliminary set of predictions, the first preliminary set of certainty information, and the second preliminary second set of certainty information to generate the set of predictions of the identification of the material sample and the corresponding set of certainty information.

12. The material identification system of claim 1 , wherein the one or more processors are configured to generate the set of predictions of the identification of the material sample in real time responsive to receipt of the first sensor data and the second sensor data.

13. The material identification system of claim 1 , further comprising one or more data storage devices including one or more databases stored thereon, the one or more databases including material identification information correlating with the first sensor data and the second sensor data, wherein the one or more processors are configured to generate the first preliminary set of predictions and the second preliminary set of predictions based, at least in part, on the material identification information of the one or more databases.

14. The material identification system of claim 13 , wherein the material identification information includes at least one of function of scattering angle information, reciprocal lattice spacing information, and chemical composition information.

15. The material identification system of claim 13 , wherein the material identification information includes at least one of structure data, chemistry data, morphology data, feature size data, and location data.

16. The material identification system of claim 1 , further comprising a scanning transmission electron microscope including the first sensor and the second sensor.

17. A method of identifying a material sample, the method comprising:
generating first sensor data using a first sensor responsive to the material sample;
generating second sensor data using a second sensor responsive to the material sample, the second sensor different from the first sensor; and
applying the first sensor data and the second sensor data to one or more neural networks for:
correlating the first sensor data to material information stored in one or more databases to generate a first preliminary set of predictions of an identity of the material sample;
correlating the second sensor data to material information stored in one or more databases to generate a second preliminary set of predictions of the identity of the material sample; and

narrowing the first preliminary set of predictions responsive to the second preliminary set of predictions to generate a set of predictions of the identity of the material sample.

18. The method of claim 17 , further comprising ranking the set of predictions of the identity of the material sample from a least likely prediction to a most likely prediction, and selecting the most likely prediction of the identity of the material sample.

19. The method of claim 17 , wherein correlating the first sensor data and the second sensor data to material information stored in one or more databases comprises processing the first sensor data and the second sensor data in parallel neural network stages of the one or more neural networks.

20. The method of claim 19 , wherein the one or more neural networks includes two chemistry stages configured to process diffraction data, a diffraction stage configured to process chemistry data, and a classification stage configured to process outputs of the two chemistry stages and the diffraction stage.

Assignees

• Battelle Energy Alliance Llc

Inventors

• Aguiar Jeffery A

Classifications

• G01N23/20058 Primary

  Measuring diffraction of electrons, e.g. low energy electron diffraction [LEED] method or reflection high energy electron diffraction [RHEED] method · CPC title

• H01J37/28

  with scanning beams {(H01J37/268, H01J37/292, H01J37/2955 take precedence)} · CPC title

• G01N2223/418

  electron microscope · CPC title

• H01J2237/2802

  Transmission microscopes · CPC title

• H01J2237/2804

  Scattered primary beam · CPC title