Full-field imaging learning machine (FILM)
Abstract
A method of determining dynamic properties of a structure (linear or nonlinear) includes receiving spatio-temporal inputs, generating mode shapes and modal components corresponding to the spatio-temporal inputs using a trained deep complexity coding artificial neural network, and subsequently generating the dynamic properties by analyzing each modal component using a trained learning machine. A computing system for non-contact determination of dynamic properties of a structure includes a camera, a processor, and a memory including computer-executable instructions. When the instructions are executed, the system is caused to receive spatio-temporal image data, decompose the spatio-temporal image data into constituent manifold components using an autoencoder, and analyze the constituent manifold components using a trained learning machine to determine the dynamic properties.
- Inventors:
- Issue Date:
- Research Org.:
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1840476
- Patent Number(s):
- 11127127
- Application Number:
- 16/429,857
- Assignee:
- UChicago Argonne, LLC (Chicago, IL)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- DOE Contract Number:
- AC02-06CH11357
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 06/03/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Yang, Yongchao. Full-field imaging learning machine (FILM). United States: N. p., 2021.
Web.
Yang, Yongchao. Full-field imaging learning machine (FILM). United States.
Yang, Yongchao. Tue .
"Full-field imaging learning machine (FILM)". United States. https://www.osti.gov/servlets/purl/1840476.
@article{osti_1840476,
title = {Full-field imaging learning machine (FILM)},
author = {Yang, Yongchao},
abstractNote = {A method of determining dynamic properties of a structure (linear or nonlinear) includes receiving spatio-temporal inputs, generating mode shapes and modal components corresponding to the spatio-temporal inputs using a trained deep complexity coding artificial neural network, and subsequently generating the dynamic properties by analyzing each modal component using a trained learning machine. A computing system for non-contact determination of dynamic properties of a structure includes a camera, a processor, and a memory including computer-executable instructions. When the instructions are executed, the system is caused to receive spatio-temporal image data, decompose the spatio-temporal image data into constituent manifold components using an autoencoder, and analyze the constituent manifold components using a trained learning machine to determine the dynamic properties.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2021},
month = {9}
}
Works referenced in this record:
A vision-based approach for the direct measurement of displacements in vibrating systems
journal, September 2003
- Wahbeh, A. Mazen; Caffrey, John P.; Masri, Sami F.
- Smart Materials and Structures, Vol. 12, Issue 5
Spatio-Temporal Features for Video Analysis
patent-application, June 2019
- Knittel, Anthony
- US Patent Application 16/211005; 20190188482
System and method for utilizing aggregated weather data for road surface condition and road friction estimates
patent, November 2020
- Roy Chowdhury, Sohini; Muppirisetty, Srikar; Ohlsson, Niklas
- US Patent Document 10,837,793
Internet-Based System and a Method for Automated Analysis of Tactile Imaging Data and Detection of Lesions
patent-application, June 2008
- Sarvazyan, Armen P.; Egorov, Vladimir; Kanilo, Sergiy
- US Patent Application 12/038041; 20080154154
System and Method for Automated Extraction of High Resolution Structural Dynamics from Video
patent-application, March 2018
- Yang, Yongchao; Kenyon, Garrett; Farrar, Charles
- US Patent Application 15/708986; 20180084195
Structure Defect Detention Using Machine Learning Algorithms
patent-application, June 2020
- Cha, Young Jin; Choi, Wooram
- US Patent Application 16/570414; 20200175352
3D digital image correlation methods for full-field vibration measurement
journal, April 2011
- Helfrick, Mark N.; Niezrecki, Christopher; Avitabile, Peter
- Mechanical Systems and Signal Processing, Vol. 25, Issue 3
Systems and Methods for a Computer Understanding Multi Modal Data Streams
patent-application, August 2016
- Yufik, Yan M.
- US Patent Application 15/147004; 20160247066
Methods, Systems, Apparatuses and Device for Facilitating Motion Analysis in a Field of Interest
patent-application, May 2019
- Leduc, Jean-Pierre
- US Patent Application 16/248418; 20190154872
Artificial neural networks for vibration based inverse parametric identifications: A review
journal, March 2017
- Hossain, Md Sazzad; Ong, Zhi Chao; Ismail, Zubaidah
- Applied Soft Computing, Vol. 52
Finite element model updating from full-field vibration measurement using digital image correlation
journal, April 2011
- Wang, Weizhuo; Mottershead, John E.; Ihle, Alexander
- Journal of Sound and Vibration, Vol. 330, Issue 8
Investigation of the dynamic characteristic of bridge structures using a computer vision method
journal, April 1999
- Olaszek, Piotr
- Measurement, Vol. 25, Issue 3
Electric Grid Analytics Learning Machine
patent-application, October 2020
- Anderson, Roger N.; Xie, Boyi; Wu, Leon L.
- US Patent Application 16/916013; 20200334577
Riesz Pyramids For Fast Phase-Based Video Magnification
patent-application, July 2015
- Wadhwa, Neal; Rubinstein, Michael; Durand, Frederic
- US Patent Application 14/592211; 20150195430
Multi-Scale Mesh Modeling Software Products and Controllers
patent-application, November 2016
- Pal, Deepankar; Patil, Nachiket; Stucker, Brent
- US Patent Application 15/105683; 20160321384