Damage characterization of carbon/carbon laminates using neural network techniques on AE signals

Philippidis, T.P.; Nikolaidis, Vasilis N.; Anastassopoulos, A. A.

doi:10.1016/s0963-8695(98)00015-2

Cited by 94 publications

(49 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various approaches with a focus on detection of characteristic similarities of the recorded signals have been published [7,24,77,[118][119][120][121][122][123][124][125][126][127][128][129][130].…”

Section: Signal Classificationmentioning

confidence: 99%

Acoustic Emission

Sause¹

2016

In Situ Monitoring of Fiber-Reinforced Composites

View full text Add to dashboard Cite

Section: Signal Classificationmentioning

confidence: 99%

Acoustic Emission

Sause¹

2016

In Situ Monitoring of Fiber-Reinforced Composites

View full text Add to dashboard Cite

“…These methods made it possible to study the delamination damage mechanisms by simultaneous consideration of the various AE features [13][14][15][16]. In another studies, [17][18] the combination of AE and mechanical information were used to recognize the behavior of damage mechanisms during delamination damage while notable results were achieved.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the damage mechanisms in mixed-mode delamination of laminated composites using acoustic emission data clustering

Fotouhi

Sadeghi

Jalalvand

et al. 2016

Journal of Thermoplastic Composite Materials

View full text Add to dashboard Cite

In this study, acoustic emission (AE) technique is used to investigate different time-to-failure mechanisms of delamination in glass/epoxy composite laminates. Woven and unidirectional layups were subjected to the double cantilever beam, end notch flexure, and mixed-mode bending tests and the generated AE signals were captured. Discrimination of the AE events, caused by different types of the damage mechanisms, was performed using wavelet packet transform (WPT) and fuzzy clustering method (FCM) associated with a principal component analysis (PCA). The FCM and WPT analyses identified three dominant damage mechanisms. Furthermore, different interface layups and different GII/GT modal ratio values (ratio of mode II strain energy release rate per total strain energy release rate) indicated different time-to-failure mechanisms incidence. Additionally, the damaged mechanisms were observed using scanning electron microscopic (SEM) analysis. The results showed that the dominant damage mechanisms in all the specimens are matrix cracking and fiber–matrix debonding. Besides, some fiber breakage appeared during the tests, and the percentage of this damage mechanism in the unidirectional specimens and mode I condition was higher than those in the woven specimens and mode II. SEM observations were also in good agreement with the obtained results. It was found that the presented methods can be utilized to improve the characterization and discrimination of damage mechanisms in the actual occurring modes of delamination in composite structures.

show abstract

“…Some researchers analysed different types of failure modes using Acoustic Emission in composites by supervised and non-supervised methods [16][17][18][19][20][21][22][23][24][25][26][27]. In supervised learning the categories, data is assigned to be known before computation.…”

Section: Introductionmentioning

confidence: 99%