Abstract
Aircraft is regarded as a collection of modern technologies from throughout all industries. However, it is inevitable to develop defects during its service life. In general, the aircraft has a periodic maintenance period, and is inspected according to a well-established process, for example non-destructive testing. However, the maintenance requires massive time and cost. If an unexpected defect occurs due to external environments before the maintenance cycle returns, it is impossible to prevent subsequent damage. This study proposes a novel real-time fatigue crack prediction method using self-sensing carbon nanotube buckypaper and deep learning algorithm. Carbon nanotube buckypaper was fabricated by the wet method. The physics-informed gated recurrent unit was used to predict real time crack growth. The physics-informed deep learning model accurately predicted the fatigue crack length. The results showed that the proposed method is promising in detecting the real-time fatigue crack growth of aircraft structure.
Similar content being viewed by others
Abbreviations
- GF :
-
Gauge factor
- R 0 :
-
Initial resistance of BP
- R :
-
Electrical measured resistance of BP
- ε :
-
Strain of specimen
- ρ :
-
Resistivity of specimen
- w :
-
Width of BP
- a :
-
Crack length
- x t :
-
Input vector
- Δa t :
-
Output vector
- ã t :
-
Candidate activation vector
- z t :
-
Update gate vector
- r t :
-
Reset gate vector
- W :
-
Parameter matrices and vector
- σ :
-
Sigmoid function
- tanh :
-
Syperbolic tangent
- ω :
-
Sength of the sequence
References
T. Dursun and C. Soutis, Recent developments in advanced aircraft aluminium alloys, Materials and Design, 56 (2014) 862–871, doi: https://doi.org/10.1016/j.matdes.2013.12.002.
H. B. Lee, T. Dinh Hoang, Y. S. Byeon, H. Jung, J. Moon and M.-S. Park, Surface stabilization of Ni-Rich layered cathode materials via surface engineering with LiTaO3 for Lithium-Ion batteries, ACS Appl. Mater. Interfaces, 14(2) (2022) 2731–2741, doi: https://doi.org/10.1021/acsami.1c19443.
J. Moon, J. Y. Jung, T. D. Hoang, D. Y. Rhee, H. B. Lee, M.-S. Park and J.-S. Yu, The correlation between particle hardness and cycle performance of layered cathode materials for lithiumion batteries, Journal of Power Sources, 486 (2021) 229359, doi: https://doi.org/10.1016/j.jpowsour.2020.229359.
A. Khan and H. S. Kim, A brief overview of delamination localization in laminated composites, Multiscale Sci. Eng., 4(3) (2022) 102–110, doi: https://doi.org/10.1007/s42493-022-00085-w.
X. Zhao, H. Gao, G. Zhang, B. Ayhan, F. Yan, C. Kwan and J. L. Rose, Active health monitoring of an aircraft wing with embedded piezoelectric sensor/actuator network: I. Defect detection, localization and growth monitoring, Smart Materials and Structures, 16(4) (2007) 1208–1217, doi: https://doi.org/10.1088/0964-1726/16/4/032.
H. Guo, G. Xiao, N. Mrad and J. Yao, Fiber optic sensors for structural health monitoring of air platforms, Sensors, 11(4) (2011) 3687–3705, doi: https://doi.org/10.3390/s110403687.
W. J. Staszewski, S. Mahzan and R. Traynor, Health monitoring of aerospace composite structures — active and passive approach, Composites Science and Technology, 69(11–12) (2009) 1678–1685, doi: https://doi.org/10.1016/j.compscitech.2008.09.034.
P. Tamilselvan and P. Wang, Failure diagnosis using deep belief learning based health state classification, Reliability Engineering and System Safety, 115 (2013) 124–135, doi: https://doi.org/10.1016/j.ress.2013.02.022.
A. Khan, N. Kim, J. K. Shin, H. S. Kim and B. D. Youn, Damage assessment of smart composite structures via machine learning: a review, Journal of Mechanical Science and Technology Advances, 1(1–2) (2019) 107–124, doi: https://doi.org/10.1007/s42791-019-0012-2.
A. Khan, I. Raouf, Y. R. Noh, D. Lee, J. W. Sohn and H. S. Kim, Autonomous assessment of delamination in laminated composites using deep learning and data augmentation, Composite Structures, 290 (2022) 115502, doi: https://doi.org/10.1016/j.compstruct.2022.115502.
A. Khan, J.-S. Kim and H. S. Kim, Damage detection and isolation from limited experimental data using simple simulations and knowledge transfer, Mathematics, 10(1) (2021) 80, doi: https://doi.org/10.3390/math10010080.
Q. Xia, Z. Zhang, Y. Liu and J. Leng, Buckypaper and its composites for aeronautic applications, Composites Part B: Engineering, 199 (2020) doi: https://doi.org/10.1016/j.compositesb.2020.108231.
L. F. de Paula Santos, R. Alderliesten, W. Kok, B. Ribeiro, J. B. de Oliveira, M. L. Costa and E. C. Botelho, The influence of carbon nanotube buckypaper/poly (ether imide) mats on the thermal properties of poly (ether imide) and poly (aryl ether ketone)/carbon fiber laminates, Diamond and Related Materials, 116 (2021) doi: https://doi.org/10.1016/j.diamond.2021.108421.
S. Datta, R. K. Neerukatti and A. Chattopadhyay, Buckypaper embedded self-sensing composite for real-time fatigue damage diagnosis and prognosis, Carbon, 139 (2018) 353–360, doi: https://doi.org/10.1016/j.carbon.2018.06.059.
I. Kang, M. J. Schulz, J. H. Kim, V. Shanov and D. Shi, A carbon nanotube strain sensor for structural health monitoring, Smart Materials and Structures, 15(3) (2006) 737–748, doi: https://doi.org/10.1088/0964-1726/15/3/009.
P. Dharap, Z. Li, S. Nagarajaiah and E. V. Barrera, Nanotube film based on single-wall carbon nanotubes for strain sensing, Nanotechnology, 15(3) (2004) 379–382, doi: https://doi.org/10.1088/0957-4484/15/3/026.
C. R. Farrar and K. Worden, An introduction to structural health monitoring, Philosophical Transactions of the Royal Society A, 365 (2007) 303–315.
A. Khan and H. S. Kim, Classification and prediction of multidamages in smart composite laminates using discriminant analysis, Mechanics of Advanced Materials and Structures, 29(2) (2022) 230–240, doi: https://doi.org/10.1080/15376494.2020.1759164.
L. Liu, L. Shen and Y. Zhou, Improving the interlaminar fracture toughness of carbon/epoxy laminates by directly incorporating with porous carbon nanotube buckypaper, Journal of Reinforced Plastics and Composites, 35(2) (2016) 165–176, doi: https://doi.org/10.1177/0731684415610919.
J. DeGraff, R. Liang, M. Q. Le, J.-F. Capsal, F. Ganet and P.-J. Cottinet, Printable low-cost and flexible carbon nanotube buckypaper motion sensors, Materials and Design, 135 (2017) 47–53.
S. Lu, D. Chen, X. Wang, X. Xiong, K. Ma, L. Zhang and Q. Meng, Monitoring the glass transition temperature of polymeric composites with carbon nanotube buckypaper sensor, Polymer Testing, 57 (2017) 12–16.
S.-C. Her and W.-C. Hsu, Strain and temperature sensitivities along with mechanical properties of CNT buckypaper sensors, Sensors, 20 (11) (2020).
K. Yang, J. He, P. Puneet, Z. Su, M. J. Skove, J. Gaillard, T. M. Tritt and A. M Rao, Tuning electrical and thermal connectivity in multiwalled carbon nanotube buckypaper, J. Phys., 22 (33) (2010).
S. Lu, D. Chen, X. Wang, J. Shao, K. Ma, L. Zhang, S. Araby and Q. Meng, Real-time cure behaviour monitoring of polymer composites using a highly flexible and sensitive CNT buckypaper sensor, Composites Science and Technology, 152 (2017) 181–189.
G. Hou, D.-G. Shang, L.-X. Zuo, L.-F. Qu, M. Xia, Y.-E. Guo, X. Yin and S.-D. Wu, Fatigue crack propagation behavior at a notch for needled C/SiC composite under tension-tension loading, Journal of Mechanical Science and Technology, 36(1) (2022) 167–177, doi: https://doi.org/10.1007/s12206-021-1215-7.
L. Zhang, X. Qu, S. Lu, X. Wang, L. Lin, Z. Zhao, Y. Lu and C. Ma, Temperature and strain monitor of COPV by buckypaper and MXene sensor combined flexible printed circuit, International Journal of Hydrogen Energy, 47(6) (2022) 4211–4221, doi: https://doi.org/10.1016/j.ijhydene.2021.10.242.
M. D. Rein, O. Breuer and H. D. Wagner, Sensors and sensitivity: Carbon nanotube buckypaper films as strain sensing devices, Composites Science and Technology, 71(3) (2011) 373–371.
X. Wang, S. Lu, K. Ma, X. Xiong, H. Zhang and M. Xu, Tensile strain sensing of buckypaper and buckypaper composites, Materials and Design, 88 (2015) 414–419.
A. Sherstinsky, Fundamentals of recurrent neural network (RNN) and long short-Term memory (LSTM) network, Physica D: Nonlinear Phenomena, 404 (2020) 132306, doi: https://doi.org/10.1016/j.physd.2019.132306.
R. G. Nascimento and F. A. C. Viana, Cumulative damage modeling with recurrent neural networks, AIAA Journal, 58(12) (2020) 5459–5471, doi: https://doi.org/10.2514/1.J059250.
J. Chung, C. Gulcehre, K. Cho and Y. Bengio, Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv:1412.3555 (2014).
J. Chung, C. Gulcehre, K. Cho and Y. Bengio, Gated feedback recurrent neural networks, ICML’15: Proceedings of the 32nd International Conference on International Conference on Machine Learning, 37 (2015) 2067–2075.
B. C. Mateus, M. Mendes, J. T. Farinha, R. Assis and A. M. Cardoso, Comparing LSTM and GRU models to predict the condition of a pulp paper press, Energies, 14(21) (2021) 6958, doi: https://doi.org/10.3390/en14216958.
C. H. Liu and S. J. Chu, Prediction of shape change of semi-elliptical surface crack by fatigue crack growth circles parameter, Journal of Mechanical Science and Technology, 28(12) (2014) 4921–4928, doi: https://doi.org/10.1007/s12206-014-1111-5.
Acknowledgments
This research was supported by the MOTIE (Ministry of Trade, Industry, and Energy) in Korea, under the Fostering Global Talents for Innovative Growth Program (P0017307) supervised by the Korea Institute for Advancement of Technology (KIAT).
Author information
Authors and Affiliations
Corresponding author
Additional information
Hyeonho Hwang received the B.S. degree in Department of Mechanical, Robotics and Energy Engineering in 2021 from Dongguk University-Seoul, Republic of Korea. His main research interest includes topics related to Prognostics and Health Management (PHM), Structural Health Monitoring (SHM), artificial intelligence, adaptive structures, structural analysis, and composite structures.
Jinwoo Song received an M.S. degree in Engineering Management from Syracuse University, Newyork, USA, in 2018, where he received a Ph.D. degree in Mechanical & Aerospace Engineering Department in 2021. His current research interests include interdisciplinary approaches to cyber-manufacturing system’s security against particular attackers from outside or inside of the system on the following toolboxes: Blockchain technology, forecasting methodology, manufacturing planning and control, inventory management, supply chain management, machine learning, big data analysis, digital twin, physical data collection/analysis, attack tree, virtual environment, and simulation.
Heung Soo Kim received the B.S. degree in Aerospace Engineering in 1997, M.S. degree in Aerospace Engineering from Inha University, Incheon, Korea, in 1999, and the Ph.D. degree from Arizona State University, Tempe, AZ in 2003. He is currently Professor with the Department of Mechanical, Robotics and Energy Engineering, Dongguk University-Seoul, Republic of Korea. His main research interest includes topics related to Prognostics and Health Management (PHM), artificial intelligence, biomimetic actuator, adaptive structures, structural analysis, numerical analysis, and composite structures. Prof. Kim is the Director of BK21 AIMS Center and DGU Global Smart Factory Center. He has published more than 300 research papers in reputed international journals and conferences. He was awarded the Academic Award at the Korean PHM Society in recognition of his contribution to academic development through outstanding research and presentation on the PHM field.
Aditi Chattopadhyay is a Regents Professor at Arizona State University and Ira A. Fulton Chair Professor of Mechanical and Aerospace Engineering. She is also the Director of Adaptive Intelligent Materials & Systems (AIMS) Center. She received her B. Tech (Hons) in Aeronautical Engineering from IIT Kharagpur, followed by M.S. and Ph.D. degrees in Aerospace Engineering from Georgia Institute of Technology, USA. Her current research areas include multifunctional materials, multiscale modeling, structural health monitoring and damage prognosis, and multiaxial fatigue. She has been the Principal Investigator on numerous grants and collaborated with defense and government laboratories on significant technical transitions.
Rights and permissions
About this article
Cite this article
Hwang, H., Song, J., Kim, H.S. et al. Real-time fatigue crack prediction using self-sensing buckypaper and gated recurrent unit. J Mech Sci Technol 37, 1401–1409 (2023). https://doi.org/10.1007/s12206-023-0226-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-0226-y