A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy
Abstract We used deep-learning-based models to automatically obtain elastic moduli from resonant ultrasound spectroscopy (RUS) spectra, which conventionally require user intervention of published analysis codes. By strategically converting theoretical RUS spectra into their modulated fingerprints an...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-04-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-33046-w |
_version_ | 1797845927898120192 |
---|---|
author | Juejing Liu Xiaodong Zhao Ke Zhao Vitaliy G. Goncharov Jerome Delhommelle Jian Lin Xiaofeng Guo |
author_facet | Juejing Liu Xiaodong Zhao Ke Zhao Vitaliy G. Goncharov Jerome Delhommelle Jian Lin Xiaofeng Guo |
author_sort | Juejing Liu |
collection | DOAJ |
description | Abstract We used deep-learning-based models to automatically obtain elastic moduli from resonant ultrasound spectroscopy (RUS) spectra, which conventionally require user intervention of published analysis codes. By strategically converting theoretical RUS spectra into their modulated fingerprints and using them as a dataset to train neural network models, we obtained models that successfully predicted both elastic moduli from theoretical test spectra of an isotropic material and from a measured steel RUS spectrum with up to 9.6% missing resonances. We further trained modulated fingerprint-based models to resolve RUS spectra from yttrium–aluminum-garnet (YAG) ceramic samples with three elastic moduli. The resulting models were capable of retrieving all three elastic moduli from spectra with a maximum of 26% missing frequencies. In summary, our modulated fingerprint method is an efficient tool to transform raw spectroscopy data and train neural network models with high accuracy and resistance to spectra distortion. |
first_indexed | 2024-04-09T17:46:52Z |
format | Article |
id | doaj.art-29c7b4b1b01d4084906befe4b3c277f6 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-09T17:46:52Z |
publishDate | 2023-04-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-29c7b4b1b01d4084906befe4b3c277f62023-04-16T11:14:33ZengNature PortfolioScientific Reports2045-23222023-04-0113111410.1038/s41598-023-33046-wA modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopyJuejing Liu0Xiaodong Zhao1Ke Zhao2Vitaliy G. Goncharov3Jerome Delhommelle4Jian Lin5Xiaofeng Guo6Department of Chemistry, Washington State UniversityDepartment of Chemistry, Washington State UniversityAlexandra Navrotsky Institute for Experimental Thermodynamics, Washington State UniversityDepartment of Chemistry, Washington State UniversityDepartment of Chemistry, University of MassachusettsSchool of Nuclear Science and Technology, Xi’an Jiaotong UniversityDepartment of Chemistry, Washington State UniversityAbstract We used deep-learning-based models to automatically obtain elastic moduli from resonant ultrasound spectroscopy (RUS) spectra, which conventionally require user intervention of published analysis codes. By strategically converting theoretical RUS spectra into their modulated fingerprints and using them as a dataset to train neural network models, we obtained models that successfully predicted both elastic moduli from theoretical test spectra of an isotropic material and from a measured steel RUS spectrum with up to 9.6% missing resonances. We further trained modulated fingerprint-based models to resolve RUS spectra from yttrium–aluminum-garnet (YAG) ceramic samples with three elastic moduli. The resulting models were capable of retrieving all three elastic moduli from spectra with a maximum of 26% missing frequencies. In summary, our modulated fingerprint method is an efficient tool to transform raw spectroscopy data and train neural network models with high accuracy and resistance to spectra distortion.https://doi.org/10.1038/s41598-023-33046-w |
spellingShingle | Juejing Liu Xiaodong Zhao Ke Zhao Vitaliy G. Goncharov Jerome Delhommelle Jian Lin Xiaofeng Guo A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy Scientific Reports |
title | A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
title_full | A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
title_fullStr | A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
title_full_unstemmed | A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
title_short | A modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
title_sort | modulated fingerprint assisted machine learning method for retrieving elastic moduli from resonant ultrasound spectroscopy |
url | https://doi.org/10.1038/s41598-023-33046-w |
work_keys_str_mv | AT juejingliu amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT xiaodongzhao amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT kezhao amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT vitaliyggoncharov amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT jeromedelhommelle amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT jianlin amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT xiaofengguo amodulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT juejingliu modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT xiaodongzhao modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT kezhao modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT vitaliyggoncharov modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT jeromedelhommelle modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT jianlin modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy AT xiaofengguo modulatedfingerprintassistedmachinelearningmethodforretrievingelasticmodulifromresonantultrasoundspectroscopy |