Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks
Discontinuous carbon fiber-carbon matrix composites dispersed Si/SiC matrix composites have complicated microstructures that consist of four phases (C/C, Si, SiC, and C/SiC). The crack stability significantly depends on their geometrical arrangement. Nondestructive evaluation is needed to maintain t...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Journal of Composites Science |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-477X/5/11/301 |
_version_ | 1797509858432385024 |
---|---|
author | Chihiro Shibata Naohiro Shichijo Johei Matsuoka Yuriko Takeshima Jenn-Ming Yang Yoshihisa Tanaka Yutaka Kagawa |
author_facet | Chihiro Shibata Naohiro Shichijo Johei Matsuoka Yuriko Takeshima Jenn-Ming Yang Yoshihisa Tanaka Yutaka Kagawa |
author_sort | Chihiro Shibata |
collection | DOAJ |
description | Discontinuous carbon fiber-carbon matrix composites dispersed Si/SiC matrix composites have complicated microstructures that consist of four phases (C/C, Si, SiC, and C/SiC). The crack stability significantly depends on their geometrical arrangement. Nondestructive evaluation is needed to maintain the components in their safe condition. Although several nondestructive evaluation methods such as the Eddy current have been developed, any set of them is still inadequate in order to cover all of the scales and aspects that (C/C)/Si/SiC composites comprise. We propose a new method for nondestructive evaluation using vibration/resonance modes and deep learning. The assumed resolution is mm-order (approx. 1–10 mm), which laser vibrometers are generally capable of handling sufficiently. We utilize deep neural networks called convolutional auto-encoders for inferring damaged areas from vibration modes, which is a so-called inverse problem and infeasible to solve numerically in most cases. We solve this inference problem by training convolutional auto-encoders using vibration modes obtained from a non-damaged specimen with various frequencies as the dataset. Experimental results show that the proposed method successfully detects the damaged areas of validation specimens. One of the noteworthy points of this method is that we need only a few specimens for training deep neural networks, which generally require a large amount of data. |
first_indexed | 2024-03-10T05:23:41Z |
format | Article |
id | doaj.art-6d0d1ed25eaa4f6abfbfe82bcd36d49f |
institution | Directory Open Access Journal |
issn | 2504-477X |
language | English |
last_indexed | 2024-03-10T05:23:41Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Composites Science |
spelling | doaj.art-6d0d1ed25eaa4f6abfbfe82bcd36d49f2023-11-22T23:52:03ZengMDPI AGJournal of Composites Science2504-477X2021-11-0151130110.3390/jcs5110301Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural NetworksChihiro Shibata0Naohiro Shichijo1Johei Matsuoka2Yuriko Takeshima3Jenn-Ming Yang4Yoshihisa Tanaka5Yutaka Kagawa6The Center for Ceramic Matrix Composites, Tokyo University of Technology, Tokyo 192-0982, JapanThe Center for Ceramic Matrix Composites, Tokyo University of Technology, Tokyo 192-0982, JapanSchool of Computer Science, Tokyo University of Technology, Tokyo 192-0982, JapanSchool of Media Science, Tokyo University of Technology, Tokyo 192-0982, JapanDepartment of Materials Science and Engineering, University of California, Los Angeles, CA 90095, USAThe Center for Ceramic Matrix Composites, Tokyo University of Technology, Tokyo 192-0982, JapanThe Center for Ceramic Matrix Composites, Tokyo University of Technology, Tokyo 192-0982, JapanDiscontinuous carbon fiber-carbon matrix composites dispersed Si/SiC matrix composites have complicated microstructures that consist of four phases (C/C, Si, SiC, and C/SiC). The crack stability significantly depends on their geometrical arrangement. Nondestructive evaluation is needed to maintain the components in their safe condition. Although several nondestructive evaluation methods such as the Eddy current have been developed, any set of them is still inadequate in order to cover all of the scales and aspects that (C/C)/Si/SiC composites comprise. We propose a new method for nondestructive evaluation using vibration/resonance modes and deep learning. The assumed resolution is mm-order (approx. 1–10 mm), which laser vibrometers are generally capable of handling sufficiently. We utilize deep neural networks called convolutional auto-encoders for inferring damaged areas from vibration modes, which is a so-called inverse problem and infeasible to solve numerically in most cases. We solve this inference problem by training convolutional auto-encoders using vibration modes obtained from a non-damaged specimen with various frequencies as the dataset. Experimental results show that the proposed method successfully detects the damaged areas of validation specimens. One of the noteworthy points of this method is that we need only a few specimens for training deep neural networks, which generally require a large amount of data.https://www.mdpi.com/2504-477X/5/11/301nondestructive evaluationvibration and resonanceanomaly detectiondeep learningconvolutional neural networksauto-encoders |
spellingShingle | Chihiro Shibata Naohiro Shichijo Johei Matsuoka Yuriko Takeshima Jenn-Ming Yang Yoshihisa Tanaka Yutaka Kagawa Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks Journal of Composites Science nondestructive evaluation vibration and resonance anomaly detection deep learning convolutional neural networks auto-encoders |
title | Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks |
title_full | Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks |
title_fullStr | Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks |
title_full_unstemmed | Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks |
title_short | Automated Damage Detection of (C/C)/Si/SiC Composite Using Vibration Modes with Deep Neural Networks |
title_sort | automated damage detection of c c si sic composite using vibration modes with deep neural networks |
topic | nondestructive evaluation vibration and resonance anomaly detection deep learning convolutional neural networks auto-encoders |
url | https://www.mdpi.com/2504-477X/5/11/301 |
work_keys_str_mv | AT chihiroshibata automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT naohiroshichijo automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT joheimatsuoka automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT yurikotakeshima automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT jennmingyang automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT yoshihisatanaka automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks AT yutakakagawa automateddamagedetectionofccsisiccompositeusingvibrationmodeswithdeepneuralnetworks |