Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission
Abstract
Prognosis techniques for prediction of remaining useful life (RUL) are of crucial importance to the management of complex systems for they can lead to appropriate maintenance interventions and improvements in reliability. While various data-driven methods have been introduced to predict the remaining useful life (RUL) of machinery systems or batteries, no research has been reported on the remaining useful strength (RUS) prediction of silicon carbide fiber reinforced silicon carbide matrix (SiCf-SiCm) materials with pivotal role in its potential usage as a structural material in nuclear reactors and turbine engines. Knowledge of its degradation process is of the utmost importance to the manufacturers. For this purpose, two approaches based on the machine-learning techniques of random-forest (RF) and convolutional neural network (CNN) are proposed to predict the RUS of SiCf-SiCm using only acoustic emission (AE) signals generated during the material’s stress applying process. Experimental results show that the CNN models achieved better predictive performance than the RF models but the latter with expert-engineered features achieves better prediction for AE signals in the early stage of degradation. Additionally, our results demonstrate that both models can correctly predict the SiCf-SiCm RUS as evaluated by our robust testing method from which the best average rootmore »
- Authors:
-
[2];
[2]
- Univ. of South Carolina, Columbia, SC (United States). Dept. of Computer Science and Engineering
- Univ. of South Carolina, Columbia, SC (United States). Dept. of Computer Science and Engineering
- Univ. of South Carolina, Columbia, SC (United States). Dept. of Mechanical Engineering
- Publication Date:
- Research Org.:
- Westinghouse Electric Company LLC, Cranberry Township, PA (United States); Univ. of South Carolina, Columbia, SC (United States)
- Sponsoring Org.:
- USDOE Office of Nuclear Energy (NE)
- OSTI Identifier:
- 1801187
- Grant/Contract Number:
- NE0008222; NE0008792
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Applied Sciences
- Additional Journal Information:
- Journal Volume: 10; Journal Issue: 8; Journal ID: ISSN 2076-3417
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; 97 MATHEMATICS AND COMPUTING; remaining useful strength; remaining useful life; silicon carbide fiber reinforced silicon carbide matrix; acoustic emission; random-forest; convolutional neural network
Citation Formats
Louis, Steph-Yves M., Nasiri, Alireza, Bao, Jingjing, Cui, Yuxin, Zhao, Yong, Jin, Jing, Huang, Xinyu, and Hu, Jianjun. Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission. United States: N. p., 2020.
Web. doi:10.3390/app10082680.
Louis, Steph-Yves M., Nasiri, Alireza, Bao, Jingjing, Cui, Yuxin, Zhao, Yong, Jin, Jing, Huang, Xinyu, & Hu, Jianjun. Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission. United States. https://doi.org/10.3390/app10082680
Louis, Steph-Yves M., Nasiri, Alireza, Bao, Jingjing, Cui, Yuxin, Zhao, Yong, Jin, Jing, Huang, Xinyu, and Hu, Jianjun. Mon .
"Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission". United States. https://doi.org/10.3390/app10082680. https://www.osti.gov/servlets/purl/1801187.
@article{osti_1801187,
title = {Remaining Useful Strength (RUS) Prediction of SiCf-SiCm Composite Materials Using Deep Learning and Acoustic Emission},
author = {Louis, Steph-Yves M. and Nasiri, Alireza and Bao, Jingjing and Cui, Yuxin and Zhao, Yong and Jin, Jing and Huang, Xinyu and Hu, Jianjun},
abstractNote = {Prognosis techniques for prediction of remaining useful life (RUL) are of crucial importance to the management of complex systems for they can lead to appropriate maintenance interventions and improvements in reliability. While various data-driven methods have been introduced to predict the remaining useful life (RUL) of machinery systems or batteries, no research has been reported on the remaining useful strength (RUS) prediction of silicon carbide fiber reinforced silicon carbide matrix (SiCf-SiCm) materials with pivotal role in its potential usage as a structural material in nuclear reactors and turbine engines. Knowledge of its degradation process is of the utmost importance to the manufacturers. For this purpose, two approaches based on the machine-learning techniques of random-forest (RF) and convolutional neural network (CNN) are proposed to predict the RUS of SiCf-SiCm using only acoustic emission (AE) signals generated during the material’s stress applying process. Experimental results show that the CNN models achieved better predictive performance than the RF models but the latter with expert-engineered features achieves better prediction for AE signals in the early stage of degradation. Additionally, our results demonstrate that both models can correctly predict the SiCf-SiCm RUS as evaluated by our robust testing method from which the best average root mean square error (RMSE) and Pearson correlation coefficient of 3.55 ksi units and 0.85 were obtained.},
doi = {10.3390/app10082680},
journal = {Applied Sciences},
number = 8,
volume = 10,
place = {United States},
year = {Mon Apr 13 00:00:00 EDT 2020},
month = {Mon Apr 13 00:00:00 EDT 2020}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
A review on machinery diagnostics and prognostics implementing condition-based maintenance
journal, October 2006
- Jardine, Andrew K. S.; Lin, Daming; Banjevic, Dragan
- Mechanical Systems and Signal Processing, Vol. 20, Issue 7
A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests
journal, April 2017
- Wu, Dazhong; Jennings, Connor; Terpenny, Janis
- Journal of Manufacturing Science and Engineering, Vol. 139, Issue 7
In-situ damage monitoring of a SiC/SiC ceramic matrix composite using acoustic emission and digital image correlation
journal, December 2016
- Whitlow, Travis; Jones, Eric; Przybyla, Craig
- Composite Structures, Vol. 158
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Prognosis of Bearing Acoustic Emission Signals Using Supervised Machine Learning
journal, July 2018
- Elforjani, Mohamed; Shanbr, Suliman
- IEEE Transactions on Industrial Electronics, Vol. 65, Issue 7
Issues and advances in SiCf/SiC composites development for fusion reactors
journal, August 2004
- Riccardi, B.; Giancarli, L.; Hasegawa, A.
- Journal of Nuclear Materials, Vol. 329-333
Characterization of indentation damage resistance of hybrid composite laminates using acoustic emission monitoring
journal, February 2017
- Suresh Kumar, C.; Arumugam, V.; Santulli, C.
- Composites Part B: Engineering, Vol. 111
Mechanical properties and real-time damage evaluations of environmental barrier coated SiC/SiC CMCs subjected to tensile loading under thermal gradients
journal, December 2015
- Appleby, M. P.; Zhu, Dongming; Morscher, G. N.
- Surface and Coatings Technology, Vol. 284
Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation
journal, November 2018
- Zhang, Ansi; Wang, Honglei; Li, Shaobo
- Applied Sciences, Vol. 8, Issue 12
Remaining useful life estimation of engineered systems using vanilla LSTM neural networks
journal, January 2018
- Wu, Yuting; Yuan, Mei; Dong, Shaopeng
- Neurocomputing, Vol. 275
Multi-bearing remaining useful life collaborative prediction: A deep learning approach
journal, April 2017
- Ren, Lei; Cui, Jin; Sun, Yaqiang
- Journal of Manufacturing Systems, Vol. 43
Online Damage Monitoring of SiC f -SiC m Composite Materials Using Acoustic Emission and Deep Learning
journal, January 2019
- Nasiri, Alireza; Bao, Jingjing; Mccleeary, Donald
- IEEE Access, Vol. 7
Strength of SiCf-SiCm composite tube under uniaxial and multiaxial loading
journal, March 2018
- Shapovalov, Kirill; Jacobsen, George M.; Alva, Luis
- Journal of Nuclear Materials, Vol. 500
Silicon carbide composites as fusion power reactor structural materials
journal, October 2011
- Snead, L. L.; Nozawa, T.; Ferraris, M.
- Journal of Nuclear Materials, Vol. 417, Issue 1-3
Machinery health prognostics: A systematic review from data acquisition to RUL prediction
journal, May 2018
- Lei, Yaguo; Li, Naipeng; Guo, Liang
- Mechanical Systems and Signal Processing, Vol. 104
Experimental study of thermo-mechanical behavior of SiC composite tubing under high temperature gradient using solid surrogate
journal, November 2015
- Alva, Luis; Shapovalov, Kirill; Jacobsen, George M.
- Journal of Nuclear Materials, Vol. 466
Acoustic emission monitoring of single cracking events and associated damage mechanism analysis in indentation and scratch testing
journal, September 1999
- von Stebut, J.; Lapostolle, F.; Bucsa, M.
- Surface and Coatings Technology, Vol. 116-119
Single-Sensor Acoustic Emission Source Localization in Plate-Like Structures Using Deep Learning
journal, May 2018
- Ebrahimkhanlou, Arvin; Salamone, Salvatore
- Aerospace, Vol. 5, Issue 2