Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms
High–speed nanoindentation rapidly generates large datasets, opening the door for advanced data analysis methods such as the resources available in artificial intelligence. The present study addresses the problem of differentiating load–displacement curves presenting pop-in, slope changes, or instab...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/3010fedbaad04314993b940bd1bdd3cd |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:3010fedbaad04314993b940bd1bdd3cd |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:3010fedbaad04314993b940bd1bdd3cd2021-11-25T18:15:46ZPop-In Identification in Nanoindentation Curves with Deep Learning Algorithms10.3390/ma142270271996-1944https://doaj.org/article/3010fedbaad04314993b940bd1bdd3cd2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1944/14/22/7027https://doaj.org/toc/1996-1944High–speed nanoindentation rapidly generates large datasets, opening the door for advanced data analysis methods such as the resources available in artificial intelligence. The present study addresses the problem of differentiating load–displacement curves presenting pop-in, slope changes, or instabilities from curves exhibiting a typical loading path in large nanoindentation datasets. Classification of the curves was achieved with a deep learning model, specifically, a convolutional neural network (CNN) model implemented in Python using TensorFlow and Keras libraries. Load–displacement curves (with pop-in and without pop-in) from various materials were input to train and validate the model. The curves were converted into square matrices (50 × 50) and then used as inputs for the CNN model. The model successfully differentiated between pop-in and non-pop-in curves with approximately 93% accuracy in the training and validation datasets, indicating that the risk of overfitting the model was negligible. These results confirmed that artificial intelligence and computer vision models represent a powerful tool for analyzing nanoindentation data.Stephania KossmanMaxence BigerelleMDPI AGarticlenanoindentationpop-inartificial intelligencedeep learningcomputer visionTechnologyTElectrical engineering. Electronics. Nuclear engineeringTK1-9971Engineering (General). Civil engineering (General)TA1-2040MicroscopyQH201-278.5Descriptive and experimental mechanicsQC120-168.85ENMaterials, Vol 14, Iss 7027, p 7027 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
nanoindentation pop-in artificial intelligence deep learning computer vision Technology T Electrical engineering. Electronics. Nuclear engineering TK1-9971 Engineering (General). Civil engineering (General) TA1-2040 Microscopy QH201-278.5 Descriptive and experimental mechanics QC120-168.85 |
spellingShingle |
nanoindentation pop-in artificial intelligence deep learning computer vision Technology T Electrical engineering. Electronics. Nuclear engineering TK1-9971 Engineering (General). Civil engineering (General) TA1-2040 Microscopy QH201-278.5 Descriptive and experimental mechanics QC120-168.85 Stephania Kossman Maxence Bigerelle Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
description |
High–speed nanoindentation rapidly generates large datasets, opening the door for advanced data analysis methods such as the resources available in artificial intelligence. The present study addresses the problem of differentiating load–displacement curves presenting pop-in, slope changes, or instabilities from curves exhibiting a typical loading path in large nanoindentation datasets. Classification of the curves was achieved with a deep learning model, specifically, a convolutional neural network (CNN) model implemented in Python using TensorFlow and Keras libraries. Load–displacement curves (with pop-in and without pop-in) from various materials were input to train and validate the model. The curves were converted into square matrices (50 × 50) and then used as inputs for the CNN model. The model successfully differentiated between pop-in and non-pop-in curves with approximately 93% accuracy in the training and validation datasets, indicating that the risk of overfitting the model was negligible. These results confirmed that artificial intelligence and computer vision models represent a powerful tool for analyzing nanoindentation data. |
format |
article |
author |
Stephania Kossman Maxence Bigerelle |
author_facet |
Stephania Kossman Maxence Bigerelle |
author_sort |
Stephania Kossman |
title |
Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
title_short |
Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
title_full |
Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
title_fullStr |
Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
title_full_unstemmed |
Pop-In Identification in Nanoindentation Curves with Deep Learning Algorithms |
title_sort |
pop-in identification in nanoindentation curves with deep learning algorithms |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/3010fedbaad04314993b940bd1bdd3cd |
work_keys_str_mv |
AT stephaniakossman popinidentificationinnanoindentationcurveswithdeeplearningalgorithms AT maxencebigerelle popinidentificationinnanoindentationcurveswithdeeplearningalgorithms |
_version_ |
1718411427744579584 |