Page 84 - IJAMD-2-3

International Journal of AI for
Materials and Design

ORIGINAL RESEARCH ARTICLE
Structural health monitoring of metal structures

using an improved carbon nanotube bucky
paper sensor and LSTM neural network

Faeez Masurkar*

Department of Engineering, Faculty of Engineering and IT, The British University in Dubai, Dubai
International Academic City, Dubai, United Arab Emirates

Abstract

In this paper, an improved fabrication method is presented for fabricating carbon
nanotube (CNT) based multi-functional bucky paper (CNT-BP) sensors that will be
primarily used for adaptive sensing in structural health monitoring applications.
A large number of BPs were fabricated using multi-walled CNTs with varying methanol-
CNT compositions, sonication times, temperatures, curing durations, membrane
thicknesses, and electrode placements to determine the optimal configuration for
large-scale production. The obtained optimal configuration of the ingredients that
yields an adequate sensitivity and ductility of the CNT-BP was then employed for
measuring the crack propagation behavior in the fatigued samples. Further, a long
short-term memory (LSTM)-based neural network was proposed for prognosis in a
*Corresponding author: metallic plate with fatigue crack propagation. The actual crack lengths of the fatigue
Faeez Masurkar crack obtained by the high-speed digital camera were correlated with that predicted
(faeez.masurkar@buid.ac.ae)
by the CNT-BP-based model and LSTM, showing good agreement. Thus, the present
Citation: Masurkar F. Structural study demonstrates that the proposed improved method of CNT-BP is highly efficient
health monitoring of metal structures
using an improved carbon nanotube in the diagnosis and prognosis of fatigue cracks in metallic structures.
bucky paper sensor and LSTM
neural network. Int J AI Mater
Design. 2025;2(3):78-87. Keywords: Carbon nanotube; Bucky paper; Adaptive sensing; Piezo-resistivity;
doi: 10.36922/IJAMD025310028 Fabrication; Structural health monitoring; Metallic structures
Received: July 29, 2025
Revised: September 2, 2025
Accepted: September 8, 2025 1. Introduction
Published online: September 23, Metallic structures undergo a variety of degradation mechanisms, such as fatigue cracks,
2025
notches, and corrosion. These cracks under the action of loads can propagate further and
Copyright: © 2025 Author(s). result in the breakage of the structure. Therefore, it is extremely important to investigate
This is an Open-Access article the health status of these structures from time to time to ensure their structural integrity
distributed under the terms of the
1-3
Creative Commons Attribution is above the required limit and avoid potential mishaps. These can be achieved in
License, permitting distribution, several ways by employing different types of sensors. One of the sensors that facilitate
and reproduction in any medium, self-sensing of the material changes is the use of a carbon nanotube (CNT)-based bucky
provided the original work is
properly cited. paper (BP) sensor for measuring the crack propagation in specimen. This type of sensor
also can be used in numerous other applications as found in literature.
Publisher’s Note: AccScience
Publishing remains neutral with Luo et al. developed an in situ structural health monitoring system for polymer
4
regard to jurisdictional claims in
published maps and institutional matrix composites using BP embedded between the laminas. The BP-based testing is
affiliations. widely used for damage and load sensing in aerospace and defense applications due to

Volume 2 Issue 3 (2025) 78 doi: 10.36922/IJAMD025310028