Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation

Francisco Maciel Monticeli; Yasmine Mosleh; John-Alan Pascoe

Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation

Francisco Maciel Monticeli^*, Yasmine Mosleh, John-Alan Pascoe

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

8 Downloads (Pure)

Abstract

This paper investigates the fatigue-induced delamination growth in carbon fibre-reinforced polymer (CFRP), considering different fibre orientation combinations. The study explores the application of Artificial Neural Networks (ANN) in the simulation of fatigue delamination behaviour to reduce the number of experimental tests required for fatigue evaluation and eventual certification. The research aims to evaluate the effectiveness of ANN at different stages of data processing, including raw data simulation and final curve estimation. The results show that applying ANN at the raw data stage provides flexibility in modelling, with error < 10%. In addition, when ANN is applied directly to the final Paris curve, it minimises errors and increases reliability, allowing for a more cost-effective fatigue evaluation process. The study highlights the importance of the data processing stages in determining the accuracy of fatigue delamination predictions with AI modelling, thus informing strategies for efficient fatigue evaluation of CFRP components in structural applications.

Original language	English
Title of host publication	Proceedings of the 21st European Conference on Composite Materials
Subtitle of host publication	Volume 8 - Special Sessions
Editors	Christophe Binetruy, Frédéric Jacquemin
Publisher	The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes.
Pages	571-578
Number of pages	8
Volume	8
ISBN (Electronic)	978-2-912985-01-9
Publication status	Published - 2024
Event	21st European Conference on Composite Materials - Cité des Congrès de Nantes, Nantes, France Duration: 2 Jul 2024 → 5 Jul 2024 Conference number: 21 https://eccm21.org/

Conference

Conference	21st European Conference on Composite Materials
Abbreviated title	ECCM21
Country/Territory	France
City	Nantes
Period	2/07/24 → 5/07/24
Internet address	https://eccm21.org/

Keywords

carbon fibre-reinforced polymer
fatigue delamination
artificial neural network
synthetic data
data processing

Access to Document

Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPsFinal published version, 1.35 MBLicence: CC BY-NC

Cite this

Monticeli, F. M., Mosleh, Y., & Pascoe, J.-A. (2024). Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation. In C. Binetruy, & F. Jacquemin (Eds.), Proceedings of the 21st European Conference on Composite Materials: Volume 8 - Special Sessions (Vol. 8, pp. 571-578). The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes..

Monticeli, Francisco Maciel ; Mosleh, Yasmine ; Pascoe, John-Alan. / Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs : Insights on Artificial Data Simulation. Proceedings of the 21st European Conference on Composite Materials: Volume 8 - Special Sessions. editor / Christophe Binetruy ; Frédéric Jacquemin. Vol. 8 The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes., 2024. pp. 571-578

@inproceedings{b912555319d14222924eb585181c8afe,

title = "Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation",

abstract = "This paper investigates the fatigue-induced delamination growth in carbon fibre-reinforced polymer (CFRP), considering different fibre orientation combinations. The study explores the application of Artificial Neural Networks (ANN) in the simulation of fatigue delamination behaviour to reduce the number of experimental tests required for fatigue evaluation and eventual certification. The research aims to evaluate the effectiveness of ANN at different stages of data processing, including raw data simulation and final curve estimation. The results show that applying ANN at the raw data stage provides flexibility in modelling, with error < 10%. In addition, when ANN is applied directly to the final Paris curve, it minimises errors and increases reliability, allowing for a more cost-effective fatigue evaluation process. The study highlights the importance of the data processing stages in determining the accuracy of fatigue delamination predictions with AI modelling, thus informing strategies for efficient fatigue evaluation of CFRP components in structural applications. ",

keywords = "carbon fibre-reinforced polymer, fatigue delamination, artificial neural network, synthetic data, data processing",

author = "Monticeli, {Francisco Maciel} and Yasmine Mosleh and John-Alan Pascoe",

year = "2024",

language = "English",

volume = "8",

pages = "571--578",

editor = "Binetruy, {Christophe } and Fr{\'e}d{\'e}ric Jacquemin",

booktitle = "Proceedings of the 21st European Conference on Composite Materials",

publisher = "The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes.",

note = "21st European Conference on Composite Materials, ECCM21 ; Conference date: 02-07-2024 Through 05-07-2024",

url = " https://eccm21.org/",

}

Monticeli, FM , Mosleh, Y & Pascoe, J-A 2024, Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation. in C Binetruy & F Jacquemin (eds), Proceedings of the 21st European Conference on Composite Materials: Volume 8 - Special Sessions. vol. 8, The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes., pp. 571-578, 21st European Conference on Composite Materials, Nantes, France, 2/07/24.

Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation. / Monticeli, Francisco Maciel ; Mosleh, Yasmine ; Pascoe, John-Alan.
Proceedings of the 21st European Conference on Composite Materials: Volume 8 - Special Sessions. ed. / Christophe Binetruy; Frédéric Jacquemin. Vol. 8 The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes., 2024. p. 571-578.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs

T2 - 21st European Conference on Composite Materials

AU - Monticeli, Francisco Maciel

AU - Mosleh, Yasmine

AU - Pascoe, John-Alan

N1 - Conference code: 21

PY - 2024

Y1 - 2024

N2 - This paper investigates the fatigue-induced delamination growth in carbon fibre-reinforced polymer (CFRP), considering different fibre orientation combinations. The study explores the application of Artificial Neural Networks (ANN) in the simulation of fatigue delamination behaviour to reduce the number of experimental tests required for fatigue evaluation and eventual certification. The research aims to evaluate the effectiveness of ANN at different stages of data processing, including raw data simulation and final curve estimation. The results show that applying ANN at the raw data stage provides flexibility in modelling, with error < 10%. In addition, when ANN is applied directly to the final Paris curve, it minimises errors and increases reliability, allowing for a more cost-effective fatigue evaluation process. The study highlights the importance of the data processing stages in determining the accuracy of fatigue delamination predictions with AI modelling, thus informing strategies for efficient fatigue evaluation of CFRP components in structural applications.

AB - This paper investigates the fatigue-induced delamination growth in carbon fibre-reinforced polymer (CFRP), considering different fibre orientation combinations. The study explores the application of Artificial Neural Networks (ANN) in the simulation of fatigue delamination behaviour to reduce the number of experimental tests required for fatigue evaluation and eventual certification. The research aims to evaluate the effectiveness of ANN at different stages of data processing, including raw data simulation and final curve estimation. The results show that applying ANN at the raw data stage provides flexibility in modelling, with error < 10%. In addition, when ANN is applied directly to the final Paris curve, it minimises errors and increases reliability, allowing for a more cost-effective fatigue evaluation process. The study highlights the importance of the data processing stages in determining the accuracy of fatigue delamination predictions with AI modelling, thus informing strategies for efficient fatigue evaluation of CFRP components in structural applications.

KW - carbon fibre-reinforced polymer

KW - fatigue delamination

KW - artificial neural network

KW - synthetic data

KW - data processing

UR - https://doi.org/10.60691/yj56-np80

M3 - Conference contribution

VL - 8

SP - 571

EP - 578

BT - Proceedings of the 21st European Conference on Composite Materials

A2 - Binetruy, Christophe

A2 - Jacquemin, Frédéric

PB - The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes.

Y2 - 2 July 2024 through 5 July 2024

ER -

Monticeli FM , Mosleh Y , Pascoe JA. Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation. In Binetruy C, Jacquemin F, editors, Proceedings of the 21st European Conference on Composite Materials: Volume 8 - Special Sessions. Vol. 8. The European Society for Composite Materials (ESCM) and the Ecole Centrale de Nantes. 2024. p. 571-578

Identifying the Most Effective Data Processing for Fatigue Delamination Growth in FRPs: Insights on Artificial Data Simulation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this