Electronic component classification

Patent metadata

Field	Value
Publication number	US-10761127-B2
Application number	US-201916533978-A
Country	US
Kind code	B2
Filing date	Aug 7, 2019
Priority date	Dec 13, 2013
Publication date	Sep 1, 2020
Grant date	Sep 1, 2020

Abstract

A system and method of electronic component authentication or component classification can reduce the vulnerability of systems (e.g., satellites, weapons, critical infrastructure, aerospace, automotive, medical systems) to counterfeits. Intrinsic deterministically random property data can be obtained from a set of authentic electronic components, processed, and clustered to create a classifier that can distinguish whether an unknown electronic component is authentic or counterfeit.

First claim

The embodiments of the invention in which an exclusive property or privilege is claimed are defined as follows:

1. A method of classifying an unknown electronic component comprising:
measuring with a sensor system, a noise signal for each of a plurality of electronic components;
building a classifier for a classification system based on the noise signals of the plurality of electronic components by segmenting each noise signal into a noise vector, transforming each noise vector into a feature vector, conducting a statistical analysis on each feature vector, and clustering the feature vectors to create the classifier;
measuring, with the sensor system a noise signal of the unknown electronic component;
classifying the unknown electronic component using the classifier and the noise signal of the unknown electronic component; and
wherein the classification system classifies the unknown electronic component according to functionality and performance characteristics.

2. The method of claim 1 wherein the classification system classifies the unknown electronic component according to thermal performance characteristics.

3. The method of claim 1 wherein the classification system classifies the unknown electronic component according to manufacturing date.

4. The method of claim 1 wherein the classification system classifies the unknown electronic component according to manufacturing equipment.

5. The method of claim 1 wherein the classification system classifies the unknown electronic component according to version, wherein the plurality of electronic components include different related versions that i) share functionality; and ii) have different combinations of subcomponents.

6. The method of claim 1 wherein the plurality of electronic components are temporarily installed one at a time into a component interface.

7. A method of classifying a plurality of unknown electronic components comprising:
measuring with a sensor system, a noise signal for each of the plurality of electronic components;
building a classifier for a classification system based on the noise signals of the plurality of electronic components by segmenting each noise signal into a noise vector, transforming each noise vector into a feature vector, conducting a statistical analysis on each feature vector, and clustering the feature vectors to create the classifier;
measuring with a sensor system, a noise signal for each of the plurality of unknown electronic components;
classifying the plurality of unknown electronic components based on the measured noise signals with the classifier; and
wherein the classification system differentiates the plurality of unknown electronic components between electronic components that have shared functionality but different performance characteristics.

8. The method of claim 7 wherein the classification system differentiates the plurality of unknown electronic components between electronic components that have different thermal performance characteristics.

9. The method of claim 8 wherein the plurality of electronic components are temporarily installed one at a time into a component interface of the electronic component authentication system and wherein the plurality of unknown electronic components are temporarily installed one at a time into the component interface of the electronic component authentication system.

10. The method of claim 8 wherein the classification system differentiates the plurality of unknown electronic components between electronic components that have identical functionality but different performance characteristics.

11. The method of claim 7 wherein the classification system differentiates the plurality of unknown electronic components between electronic components that have different manufacturing dates.

12. The method of claim 7 wherein the classification system differentiates the plurality of unknown electronic components between electronic components manufactured by different equipment.

13. The method of claim 7 wherein the classification system differentiates the plurality of unknown electronic components between different related versions of electronic components, wherein the plurality of electronic components include different related versions that i) share functionality; and ii) have different combinations of subcomponents.

14. The method of claim 7 wherein the classification system differentiates the plurality of unknown electronic components between electronic components that have different functionality.

15. A method of classifying an unknown electronic component comprising:
measuring, with a sensor system, a noise signal for each of a plurality of known electronic components;
building a classifier for a classification system based on the noise signals of the plurality of known electronic components by segmenting each noise signal into a noise vector, transforming each noise vector into a feature vector, conducting a statistical analysis on each feature vector, and clustering the feature vectors to create the classifier, wherein the classifier differentiates between electronic components that share functionality but have different performance characteristics;
measuring, with the sensor system, a noise signal of the unknown electronic component; and
classifying the unknown electronic component using the classification system and the noise signal of the unknown electronic component.

16. The method of claim 15 wherein the classification system classifies the unknown electronic component according to thermal performance characteristics.

17. The method of claim 15 wherein the classification system classifies the unknown electronic component according to manufacturing date.

18. The method of claim 15 wherein the classification system classifies the unknown electronic component according to manufacturing equipment.

19. The method of claim 15 wherein the classification system classifies the unknown electronic component according to version, wherein the plurality of known electronic components include different related versions that i) share functionality; and ii) have different combinations of subcomponents.

20. The method of claim 15 wherein the plurality of known electronic components are temporarily installed one at a time into a component interface.

Assignees

• Battelle Memorial Institute

Inventors

• House Larry J
• Engelhart Dale C

Classifications

• G06F2218/12

  Classification; Matching · CPC title

• G06V20/80 Primary

  Recognising image objects characterised by unique random patterns · CPC title

• G01R29/26 Primary

  Measuring noise figure; Measuring signal-to-noise ratio · CPC title

• G06F18/24147

  Distances to closest patterns, e.g. nearest neighbour classification · CPC title

• G06F21/44

  Program or device authentication · CPC title