Acoustic signature management engine in an object integrity sensing system

Patent metadata

Field	Value
Publication number	US-2022412923-A1
Application number	US-202117362756-A
Country	US
Kind code	A1
Filing date	Jun 29, 2021
Priority date	Jun 29, 2021
Publication date	Dec 29, 2022
Grant date	—

Abstract

Methods, systems, and computer storage media for providing an indication of an integrity of an object based on a non-invasive assessment of the integrity of the object using acoustic signature management engine in object integrity sensing system. In operation, an aggregate object-intermediate-medium sound of an object in an intermediate medium is detected (e.g., via sensors). An acoustic signature of the aggregate object-intermediate-medium sound is generated as a processed acoustic channel associated with statistical measurements. A reference acoustic signature of the object and intermediate medium is accessed. The reference acoustic signature is associated with an acoustic signature computation model, that generates reference acoustic signatures based on a mean and standard deviation measurements of input signals transmitted through the object and intermediate medium. A determination whether the object has impaired integrity is determined based on a quantified difference between the acoustic signature of the aggregate object-intermediate-medium sound and the reference acoustic signature.

First claim

What is claimed is:

1 . A computer-implemented method, the method comprising:
transmitting an input signal through an intermediate medium and through an object associated with the intermediate medium; in response to transmitting the input signal, detecting, via a sensor, an aggregate object-intermediate-medium sound; generating an acoustic signature corresponding to aggregate object-intermediate-medium sound; accessing a reference acoustic signature corresponding to the object and the intermediate medium; comparing the reference acoustic signature to the acoustic signature to generate a quantified difference between the reference acoustic signature and the acoustic signature; and communicate an indication of an integrity of the object based on the quantified difference between the reference acoustic signature and the acoustic signature.

2 . The method of claim 1 , wherein the input signal is an input signal that is transmitted via a transducer that is physically attached to the intermediate medium, wherein the transducer is not physically attached to the object.

3 . The method of claim 2 , wherein the transducer is physically attached to an optimal location associated with the intermediate medium, wherein the optimal location is determined based on:
determining a location of the intermediate medium using a camera; detecting a location of the object within the intermediate medium using a radar; and based on the location intermediate medium and the location of the object, determining the optimal location for physically attaching the transducer to the intermediate medium, wherein the optimal location is a location identified for maximum energy transfer from the transducer to the intermediate medium and the object.

4 . The method of claim 1 , wherein the object comprises a fragile material having a low noise reduction coefficient measurement, wherein the intermediate medium comprises a material that is transparent to mm-waves, and wherein the aggregate object-intermediate-medium sound comprises a frequency response of the fragile material of the object to the input signal.

5 . The method of claim 1 , wherein the reference acoustic signature and the acoustic signature are generated, using an acoustic signature computation model, based on acoustic responses in a frequency domain, mean measurements, and standard deviation measurements for corresponding input signals.

6 . The method of claim 1 , wherein generating the quantified difference is between the reference acoustic signature and the acoustic signature based on determining a distance metric associated with a difference between a mean frequency for the acoustic signature and a mean frequency for the reference acoustic signature.

7 . The method of claim 6 , the method further comprising determining that the object has an impaired integrity is based a threshold, wherein the threshold is based on the distance metric and individual channel measurements used to generate the reference acoustic signature.

8 . A computerized system, the system comprising:
one or more computer processors; and computer memory storing computer-useable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising: receiving, via a first multi-location object integrity sensing client, a first acoustic signature associated with a package comprising an object in an intermediate medium; receiving, via a second multi-location object integrity sensing client, a second acoustic signature associated with the package; accessing a reference acoustic signature corresponding to the object and the intermediate medium; comparing the reference acoustic signature to the first acoustic signature and the second acoustic signature to generate a quantified difference between the reference acoustic signature and the first acoustic signature and a quantified difference between the reference acoustic signature and the second acoustic signature, respectively; and based on the quantified difference between the reference acoustic signature and the first acoustic signature the quantified difference between the reference acoustic signature and the second acoustic signature, communicate a first indication of an integrity of the object at the first location or a second indication of an integrity of the object at the second location.

9 . The system of claim 8 , wherein the first acoustic signature and the second acoustic signature are associated with corresponding input signals, wherein input signals are transmitted via transducers that are physically attached to the intermediate medium, wherein the transducer is not physically attached to the object.

10 . The system of claim 8 , wherein the first indication of the integrity of the object is associated with an identifier of the first location and the second indication of the integrity of the object is associated with an identifier of the second location.

11 . The system of claim 8 , wherein the object comprises a fragile material having a low noise reduction coefficient measurement, wherein the intermediate medium comprises a material that is transparent to mm-waves, and wherein the aggregate object-intermediate-medium sound comprises a frequency response of the fragile material of the object to the input signal.

12 . The system of claim 8 , wherein the reference acoustic signature is generated, using an acoustic signature computation model, based on acoustic responses in a frequency domain, mean measurements, and standard deviation measurements for corresponding input signals.

13 . The system of claim 8 , wherein generating the quantified difference between the reference acoustic signature and the acoustic signature is based on determining a distance metric associated with a difference between a mean frequency for the acoustic signature and a mean frequency for the reference acoustic signature.

14 . The system of claim 13 , wherein the first indication or the second indication indicates that the object has an impaired integrity is based on a threshold, wherein the threshold is based on the distance metric and individual channel measurements used to generate the reference acoustic signature.

15 . One or more computer-storage media having computer-executable instructions embodied thereon that, when executed by a computing system having a processor, and memory, cause the processor to:
accessing an acoustic signature corresponding to an object associated with an intermediate medium; accessing a reference acoustic signature corresponding to the object and the intermediate medium; comparing the reference acoustic signature to the acoustic signature to generate a quantified difference between the reference acoustic signature and the acoustic signature; and communicating an indication of an integrity of the object based on the quantified difference between the reference acoustic signature and the acoustic signature.

16 . The media of claim 15 , wherein the reference acoustic signature is generated, using an acoustic signature computation model, based on acoustic responses in a frequency domain, mean measurements, and standard deviation measurements for corresponding input signals.

17 . The media of claim 16 , further comprising an acoustic signature comparison computation model that operates based on a similarity metric and a clustering algorithm that are used to determine the difference between the quantified difference between the reference acoustic signature and the acoustic signature and a threshold for determinin

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Vasisht Deepak
• Chandra Ranveer
• Kotaru Manikanta
• Priyantha Nissanka Arachchige Bodhi
• Gadre Akshay Sanjay
• Raghuvanshi Nikunj

Classifications

• G01N29/4454

  Signal recognition, e.g. specific values or portions, signal events, signatures · CPC title

• G01N29/348

  with frequency characteristics, e.g. single frequency signals, chirp signals (measuring frequency of mechanical vibrations or acoustic waves in general G01H1/06, G01H3/04; measuring frequency or analysing frequency spectra G01R23/00) · CPC title

• G01N29/4436

  with a reference signal (amplitude comparison G01N29/48) · CPC title

• G01N29/343

  pulse waves, e.g. particular sequence of pulses, bursts · CPC title

• G01N29/12

  by measuring frequency or resonance of acoustic waves {(measuring frequency or resonant frequency of mechanical vibrations or acoustic waves in general G01H1/06, G01H3/04, G01H13/00; acoustic resonators G10K11/04; vibration or shock testing of structures G01M7/00)} · CPC title