ACOUSTIC FINGERPRINTING OF MECHANICAL DEVICES

• US 20100080086A1
• Filed: 07/27/2009
• Published: 04/01/2010
• Est. Priority Date: 10/01/2008
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Wright, George L., Wright, Mark A.
• Granted Patent: US 8,983,677 B2
• Time in Patent Office: Days
• US Class Current: 367/191
• CPC Class Codes: H04B 11/00 Transmission systems employing sonic, ultrasonic or infrasonic waves
• CPC Class Codes: H04K 1/00 Secret communication
• CPC Class Codes: H04K 2203/22 for communication related to vehicles
• CPC Class Codes: H04K 3/45 characterized by including monitoring of the target or target signal, e.g. in reactive jammers or follower jammers for example by means of an alternation of jamming phases and monitoring phases, called "look-through mode"

Abstract

A method and device are presented for identifying machines, such as vehicles, based on acoustic machine signatures. An acoustic sensor generates machine-acoustic data about the machine. A machine-signature identifier receives the machine-acoustic data, determines a machine signature from the machine-acoustic data, and identifies the machine based on the machine signature. A machine-signature database, configured to store multiple machine signatures and/or machine-signature templates, may receive and process queries about machine signatures for machine identification. The machine-signature identifier may generate and send an instruction based on the identified machine. The instruction may instruct application of electronic countermeasures or may permit a vehicle to enter a secured area. An acoustic modulator may generate the machine-acoustic data to act as a machine signature. The acoustic modulator may generate the machine signature using an ultrasonic carrier.

Claims

1. A method, comprising:

receiving machine-acoustic data from one or more acoustic sensors about a machine;

determining a machine signature based on the machine-acoustic data at an acoustic-signature identifier;

identifying the machine based on the machine signature at the acoustic-signature identifier; and

sending an instruction from the acoustic-signature identifier based on the identified machine.

2. The method of claim 1, wherein identifying the machine comprises searching for the machine signature among a plurality of machine signatures, wherein the plurality of machine signatures are stored in a database on a computing device.

3. The method of claim 2, wherein identifying the machine comprises determining a partial identification of the machine signature based on the plurality of machine signatures.

4. The method of claim 2, wherein the partial identification is based on a machine-aging model.

5. The method of claim 2, further comprising:

responsive to finding the machine signature in the stored plurality of machine signatures, generating the instruction.

6. The method of claim 4, wherein the instruction is an instruction to apply a countermeasure.

7. The method of claim 1, wherein the machine-acoustic data comprises acoustic data from machine sound waves.

8. The method of claim 7, wherein the machine-acoustic data further comprises modulated acoustic data.

9. The method of claim 8, wherein the modulated acoustic data is specific to the machine.

10. The method of claim 8, wherein the machine signature is based on the modulated acoustic data.

11. The method of claim 8, wherein the modulated acoustic data utilizes an ultrasound frequency as a carrier.

12. A machine-signature identifier, comprising:

a processor;

data storage;

a network-communication interface;

machine language instructions stored in the data storage and executable by the processor to perform functions including;

receiving machine-acoustic data about a machine,

determining a machine signature based on the machine-acoustic data,

identifying the machine based on the machine signature,

generating an instruction based on the identified machine, and

sending the instruction via the network-communication interface.

13. The machine-signature identifier of claim 12, further comprising a sensor interface, and wherein receiving machine-acoustic data comprises receiving machine-acoustic data from the sensor interface.

14. The machine-signature identifier of claim 12, wherein receiving machine-acoustic data comprises receiving machine-acoustic data from the network-communication interface.

15. The machine-signature identifier of claim 12, wherein the data storage is configured to store a machine-signature database, and wherein the machine-signature database is configured to store a plurality of machine signatures.

16. The machine-signature identifier of claim 15, wherein identifying the machine based on the machine signature comprises:

generating a query, the query comprising the machine signature;

searching the machine-signature database based on the query;

responsive to the machine-signature database search, receiving a query result; and

identifying the machine based on the query result.

17. The machine-signature identifier of claim 15, wherein the machine-signature database is configured to store a plurality of machine signatures for the machine, and wherein the plurality of machine signatures comprises a delta signature for the machine.

18. The machine-signature identifier of claim 17, wherein the plurality of machine signatures for the machine comprise a baseline-machine signature and one or more updated-machine signatures.

19. The machine-signature identifier of claim 15, wherein the machine-signature database is configured to store a plurality of machine-signature templates, and wherein searching the data base comprises comparing the machine signature to one or more of the plurality of machine-signature templates.

20. The machine-signature identifier of claim 19, wherein identifying the machine comprises:

responsive to the comparing the machine signature to one or more of the plurality of machine-signature templates, determining that the machine signature matches a given machine-signature template of the plurality of machine-signature templates; and

determining a partial identification of the machine based on the given machine-signature template.