Damage mechanism identification in composites via machine learning and acoustic emission

被引：81

作者：

Muir, C. ^{[1
]}

Swaminathan, B. ^{[1
]}

Almansour, A. S. ^{[2
]}

Sevener, K. ^{[3
]}

Smith, C. ^{[2
]}

Presby, M. ^{[2
]}

Kiser, J. D. ^{[2
]}

Pollock, T. M. ^{[1
]}

Daly, S. ^{[4
]}

机构：

[1] Univ Calif Santa Barbara, Mat Dept, Santa Barbara, CA USA

[2] NASA, Glenn Res Ctr, Cleveland, OH USA

[3] Univ Michigan, Mat Sci & Engn Dept, Ann Arbor, MI 48109 USA

[4] Univ Calif Santa Barbara, Dept Mech Engn, Santa Barbara, CA 93106 USA

来源：

NPJ COMPUTATIONAL MATERIALS | 2021年 / 7卷 / 01期

基金：

美国国家科学基金会;

关键词：

PATTERN-RECOGNITION APPROACH; FIBER-REINFORCED COMPOSITE; CERAMIC-MATRIX COMPOSITES; HILBERT-HUANG TRANSFORM; SELF-ORGANIZING MAP; FAILURE MODES; WAVELET TRANSFORM; CLUSTER-ANALYSIS; TENSILE TESTS; K-MEANS;

D O I：

10.1038/s41524-021-00565-x

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

Damage mechanism identification has scientific and practical ramifications for the structural health monitoring, design, and application of composite systems. Recent advances in machine learning uncover pathways to identify the waveform-damage mechanism relationship in higher-dimensional spaces for a comprehensive understanding of damage evolution. This review evaluates the state of the field, beginning with a physics-based understanding of acoustic emission waveform feature extraction, followed by a detailed overview of waveform clustering, labeling, and error analysis strategies. Fundamental requirements for damage mechanism identification in any machine learning framework, including those currently in use, under development, and yet to be explored, are discussed.

引用

页数：15

共 50 条

[31] Acoustic Emission as a Tool for Damage Identification and Characterization in Glass Reinforced Cross Ply Laminates
D. G. Aggelis
N.-M. Barkoula
T. E. Matikas
A. S. Paipetis
Applied Composite Materials, 2013, 20 : 489 - 503
[32] Acoustic Emission as a Tool for Damage Identification and Characterization in Glass Reinforced Cross Ply Laminates
Aggelis, D. G.
Barkoula, N-M
Matikas, T. E.
Paipetis, A. S.
APPLIED COMPOSITE MATERIALS, 2013, 20 (04) : 489 - 503
[33] Wavelet transform of acoustic emission signals in failure of model composites
Ni, QQ
Iwamoto, M
ENGINEERING FRACTURE MECHANICS, 2002, 69 (06) : 717 - 728
[34] Study on interfacial debonding stress and damage mechanisms of C/SiC composites using acoustic emission
Li, Yuanchen
Liu, Xiao
Chen, Guang
Ren, Chengzu
CERAMICS INTERNATIONAL, 2021, 47 (04) : 4512 - 4520
[35] Analysis of the damage mechanisms in mixedmode delamination of laminated composites using acoustic emission data clustering
Fotouhi, Mohamad
Sadeghi, Seyedali
Jalalvand, Meisam
Ahmadi, Mehdi
JOURNAL OF THERMOPLASTIC COMPOSITE MATERIALS, 2017, 30 (03) : 318 - 340
[36] Damage characterization of CFRP laminates using acoustic emission and digital image correlation: Clustering, damage identification and classification
Andraju, Lala Bahadur
Raju, Gangadharan
ENGINEERING FRACTURE MECHANICS, 2023, 277
[37] Investigation on damage evolution of open-hole plain woven composites under tensile load by acoustic emission signal analysis
Liu, Yuhang
Zhang, Li
Li, Zhixing
Chen, Zhanguang
Huang, Kai
Guo, Licheng
COMPOSITE STRUCTURES, 2023, 305
[38] Fatigue damage monitoring for basalt fiber reinforced polymer composites using acoustic emission technique
Wang, Wentao
Li, Hui
Qu, Zhi
HEALTH MONITORING OF STRUCTURAL AND BIOLOGICAL SYSTEMS 2012, 2012, 8348
[39] Matrix cracking onset stress and strain as a function of temperature, and characterisation of damage modes in SiCf/SiC ceramic matrix composites via acoustic emission
Quiney, Z.
Jeffs, S. P.
Gale, L.
Pattison, S.
Bache, M. R.
JOURNAL OF THE EUROPEAN CERAMIC SOCIETY, 2023, 43 (07) : 2958 - 2967
[40] Intelligent identification of machining damage in ceramic matrix composites based on deep learning
Mao, Weiming
Zhou, Kun
COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING, 2024, 187

← 1 2 3 4 5 →