Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning
Dynamic cracking along an interface of brittle material is a fundamental knowledge of rock faulting but remain largely enigmatic. Laboratory investigation of the extremely fast process requires the use of advanced high-speed photography, which limits wide participation in this research. This study a...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/179148 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-179148 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1791482024-07-22T02:30:48Z Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning Tie, Jiahao Wu, Wei School of Civil and Environmental Engineering Engineering Machine learning Data augmentation Dynamic cracking along an interface of brittle material is a fundamental knowledge of rock faulting but remain largely enigmatic. Laboratory investigation of the extremely fast process requires the use of advanced high-speed photography, which limits wide participation in this research. This study applies image data augmentation and Convolutional Neural Network (CNN) to assist high-speed photography for detection of crack tip location, extending the capability of high-speed photography with a low frame rate to achieve a high prediction accuracy. The prediction accuracy generally increases with a smaller kernel size to produce more image slices for model training, but the kernel size exists a lower limit for reasonable prediction, which is 0.8 × 30 mm in our study. The selection of kernel size is particularly important for a less advanced camera with a frame rate lower than 70,000 frame-per-second. Additionally, the digital image correlation technique can assist the identification of crack tip location on low-resolution images to provide image slices with precise information of crack tip for model training. Robust CNN models can be built with multiple static and dynamic loadings, different image resolutions, and various heterogeneous rock materials and used to construct a graphic reference for researchers to evaluate the best performance of high-speed photography and machine learning-assisted performance improvement. Ministry of Education (MOE) This research is supported by Ministry of Education of Singapore, under Academic Research Fund Tier 1 (Grant Number RG143/23). 2024-07-22T02:30:48Z 2024-07-22T02:30:48Z 2024 Journal Article Tie, J. & Wu, W. (2024). Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning. International Journal of Rock Mechanics and Mining Sciences, 179, 105784-. https://dx.doi.org/10.1016/j.ijrmms.2024.105784 1365-1609 https://hdl.handle.net/10356/179148 10.1016/j.ijrmms.2024.105784 2-s2.0-85194944448 179 105784 en RG143/23 International Journal of Rock Mechanics and Mining Sciences © 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Machine learning Data augmentation |
spellingShingle |
Engineering Machine learning Data augmentation Tie, Jiahao Wu, Wei Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
description |
Dynamic cracking along an interface of brittle material is a fundamental knowledge of rock faulting but remain largely enigmatic. Laboratory investigation of the extremely fast process requires the use of advanced high-speed photography, which limits wide participation in this research. This study applies image data augmentation and Convolutional Neural Network (CNN) to assist high-speed photography for detection of crack tip location, extending the capability of high-speed photography with a low frame rate to achieve a high prediction accuracy. The prediction accuracy generally increases with a smaller kernel size to produce more image slices for model training, but the kernel size exists a lower limit for reasonable prediction, which is 0.8 × 30 mm in our study. The selection of kernel size is particularly important for a less advanced camera with a frame rate lower than 70,000 frame-per-second. Additionally, the digital image correlation technique can assist the identification of crack tip location on low-resolution images to provide image slices with precise information of crack tip for model training. Robust CNN models can be built with multiple static and dynamic loadings, different image resolutions, and various heterogeneous rock materials and used to construct a graphic reference for researchers to evaluate the best performance of high-speed photography and machine learning-assisted performance improvement. |
author2 |
School of Civil and Environmental Engineering |
author_facet |
School of Civil and Environmental Engineering Tie, Jiahao Wu, Wei |
format |
Article |
author |
Tie, Jiahao Wu, Wei |
author_sort |
Tie, Jiahao |
title |
Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
title_short |
Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
title_full |
Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
title_fullStr |
Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
title_full_unstemmed |
Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
title_sort |
intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/179148 |
_version_ |
1806059796281950208 |