Multilayer deep neural network modeling of fatigue crack growth in proton exchange membrane

Song, P, Li, W, Cai, L, Serjouei, A ORCID: https://orcid.org/0000-0002-7250-4131, Jin, Y, Elbugdady, I and Cao, X, 2026. Multilayer deep neural network modeling of fatigue crack growth in proton exchange membrane. Journal of Applied Polymer Science: e70404. ISSN 0021-8995

Text 2560936_Serjouei.pdf - Post-print Full-text access embargoed until 19 January 2027. Download (3MB)

Abstract

This work proposes a novel hybrid multi‑layer deep neural network that integrates Convolutional Neural Network (CNN), Bi-directional Long Short-Term Memory (BiLSTM), and Self‑Attention to capture the cross‑scale interactions between macroscopic crack growth and mesoscopic plastic‑zone evolution, enabling accurate and interpretable prediction of frequency‑dependent fatigue crack growth in Proton exchange membrane (PEM). PEM is one of the most crucial polymer materials for electrochemical devices. However, fatigue-induced mechanical degradation significantly compromises its safety and durability. Unfortunately, the intelligent damage assessment methodologies associated with multi-scale fatigue crack growth behavior of PEM are not yet fully understood. To address this, based on the in-situ DIC fatigue testing with four loading frequencies, a hybrid deep learning framework that integrates physical insights and time-series modeling is proposed to predict the fatigue crack growth. Results show clear time-dependent fatigue crack growth behavior. With increasing frequency, the macroscale crack growth rate decreases, while the mesoscopic cyclic plastic zone size increases. The proposed approach comprises six components: (1) Data collection and preprocessing, (2) Hybrid neural network modeling, (3) Prediction performance evaluation, (4) Small sample optimization, (5) Generalization verification, and (6) Shapley Additive Explanations (SHAP) analysis. Comparative model evaluations confirm the framework's predictive accuracy. SHAP analysis identifies loading frequency and plastic zone size as critical factors influencing crack evolution, corresponding to a "small plastic zone—slow growth" regime at high frequencies and a "large plastic zone—rapid growth" regime at low frequencies.

Item Type:	Journal article
Publication Title:	Journal of Applied Polymer Science
Creators:	Song, P., Li, W., Cai, L., Serjouei, A., Jin, Y., Elbugdady, I. and Cao, X.
Publisher:	Wiley
Date:	19 January 2026
Volume:	0
ISSN:	0021-8995
Identifiers:	Number Type 10.1002/app.70404 DOI 2560936 Other
Rights:	This is the peer reviewed version of the following article: Song, P., Li, W., Cai, L., Serjouei, A., Jin, Y., Elbugdady, I., & Cao, X. (2026). Multilayer deep neural network modeling of fatigue crack growth in proton exchange membrane. Journal of Applied Polymer Science, e70404, which has been published in final form at https://doi.org/10.1002/app.70404 This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited.
Divisions:	Schools > School of Science and Technology
Record created by:	Laura Borcherds
Date Added:	23 Jan 2026 15:33
Last Modified:	23 Jan 2026 15:33
URI:	https://irep.ntu.ac.uk/id/eprint/55113

Actions (login required)

Edit View

Statistics

Views

Downloads