# US 11,906,468 B2 · Acoustic profiling techniques for non-destructive testing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,906,468 B2 - Document ID: US11906468B2 - Status: Granted - Kind: B2 - Application number: 17/649,818 - Filed: 2022-02-03 - Published: 2022-10-27 - Granted: 2024-02-20 - Earliest claimed: 2021-04-23 - Assignees: Evident Canada, Inc. - Applicants: Evident Canada, Inc. - Inventors: Ivan C. Kraljic; Benoit Lepage; Guillaume Painchaud-April - Web page: https://patentgrep.com/patent/US11906468B2 ## CPC - G01N 29/0654: {Imaging} - G01N 29/4481: {Neural networks} - G01N 29/07: by measuring propagation velocity or propagation time of acoustic waves - G01N 29/2437: {Piezoelectric probes} - G01N 29/262: {by electronic orientation or focusing, e.g. with phased arrays (phased arrays per se G10K11/34)} - G06N 20/00: Machine learning - G01N 2291/011: Velocity or travel time - G01N 2291/023: Solids - G01N 2291/0231: Composite or layered materials - G01N 2291/02854: Length, thickness - G01N 2291/0289: Internal structure, e.g. defects, grain size, texture - G01N 2291/106: one or more transducer arrays - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An acoustic inspection system can be used to generate a surface profile of a component under inspection, and then can be used to perform the inspection on the component. The acoustic inspection system can obtain acoustic imaging data, e.g., FMC data, of the component. Then, the acoustic inspection system can apply a previously trained machine learning model to an encoded acoustic image, such as a TFM image, to generate a representation of the profile of one or more surfaces of the component. In this manner, no additional equipment is needed, which is more convenient and efficient than implementations that utilize additional components that are external to the acoustic inspection system. ## Claims ### Claim 1 A computerized method of automatically determining a representation of a profile of a surface of an object using a trained machine learning model, the method comprising: obtaining acoustic imaging data of the object; generating, using the acoustic imaging data and a time-of-flight (TOF) delay associated with a medium, a first encoded acoustic image of the object; and applying a previously trained machine learning model to the first encoded acoustic image to generate the representation of the profile of the surface. ### Claim 2 (depends on 1) The computerized method of claim 1, wherein the representation of the profile of the surface includes an image of the profile of the surface, and wherein the image includes pixels. ### Claim 3 (depends on 2) The computerized method of claim 2, comprising: performing a curve fitting using the image of the profile of the surface; recomputing the TOF delay based on the curve fitting; and generating a second encoded acoustic image of the object using the recomputed TOF delay. ### Claim 4 (depends on 1) The computerized method of claim 1, wherein obtaining the acoustic imaging data includes: performing acoustic acquisition techniques to obtain the acoustic imaging data. ### Claim 5 (depends on 1) The computerized method of claim 1, wherein the first encoded acoustic image is a total focusing method (TFM) image. ### Claim 6 (depends on 1) The computerized method of claim 1, wherein obtaining acoustic imaging data of the object includes: obtaining acoustic imaging data of the object using full matrix capture techniques. ### Claim 7 (depends on 1) The computerized method of claim 1, wherein obtaining acoustic imaging data of the object includes: obtaining acoustic imaging data of the object using virtual source aperture techniques. ### Claim 8 (depends on 1) The computerized method of claim 1, wherein obtaining acoustic imaging data of the object includes: obtaining acoustic imaging data of the object using half matrix capture techniques. ### Claim 9 (depends on 1) The computerized method of claim 1, wherein obtaining acoustic imaging data of the object includes: obtaining acoustic imaging data of the object using plane wave imaging capture techniques. ### Claim 10 An ultrasound inspection system for automatically determining a representation of a profile of a surface of an object using a trained machine learning model, the system comprising: an ultrasonic probe assembly; and a processor in communication with the ultrasonic probe assembly, the processor configured for: obtaining acoustic imaging data of the object generating, using the acoustic imaging data and a time-of-flight (TOF) delay associated with a medium, a first encoded acoustic image of the object; and applying a previously trained machine learning model to the first encoded acoustic image to generate the representation of the profile of the surface. ### Claim 11 (depends on 10) The system of claim 10, wherein the representation of the profile of the surface includes an image of the profile of the surface, and wherein the image includes pixels. ### Claim 12 (depends on 11) The system of claim 11, wherein the processor is further configured for: performing a curve fitting using the image of the profile of the surface; recomputing the TOF delay based on the curve fitting; and generating a second encoded acoustic image of the object using the recomputed TOF delay. ### Claim 13 (depends on 10) The system of claim 10, wherein the processor configured for obtaining the acoustic imaging data is configured for: performing acoustic acquisition techniques to obtain the acoustic imaging data. ### Claim 14 (depends on 10) The system of claim 10, wherein the first encoded acoustic image is a total focusing method (TFM) image. ### Claim 15 (depends on 10) The system of claim 10, wherein the processor configured for obtaining acoustic imaging data of the object is configured for: obtaining acoustic imaging data of the object using full matrix capture techniques. ### Claim 16 (depends on 10) The system of claim 10, wherein the processor configured for obtaining acoustic imaging data of the object is configured for: obtaining acoustic imaging data of the object using virtual source aperture techniques. ### Claim 17 (depends on 10) The system of claim 10, wherein the processor configured for obtaining acoustic imaging data of the object is configured for: obtaining acoustic imaging data of the object using half matrix capture techniques. ### Claim 18 (depends on 10) The system of claim 10, wherein the processor configured for obtaining acoustic imaging data of the object is configured for: obtaining acoustic imaging data of the object using plane wave imaging capture techniques. ### Claim 19 (depends on 10) The system of claim 10, wherein the representation of the profile of the surface represents a geometric shape or a contour of at least a portion of the profile of the surface.