Artificial Intelligence based Augmented Structural Health Monitoring in Smart Materials Using Deep Temporal Learning Networks
Mithra C
Department of Computational Intelligence, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India.
Department of Computer Science and Engineering, School of Computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (Deemed to be University), Avadi, Chennai, Tamil Nadu, India.
Structural Health Monitoring (SHM) in smart materials faces significant challenges in real-time damage detection due to complex temporal dependencies and multi-physics correlations in degradation processes that traditional handcrafted feature approaches fail to capture effectively. This study develops a novel AI-augmented SHM framework integrating deep temporal learning networks with embedded multi-modal sensor systems for comprehensive damage characterization in Carbon Fiber Reinforced Polymer (CFRP) materials. The proposed hybrid architecture combines temporal convolutional layers, Bidirectional Gated Recurrent Units (BiGRU), and attention mechanisms to process synchronized data from strain, vibration, Acoustic Emission (AE), and temperature sensors through a multi-task learning approach addressing damage detection, severity classification, and 3D spatial localization simultaneously. Experimental validation using controlled damage protocols on instrumented CFRP specimens demonstrated exceptional performance: 94.2% damage detection accuracy (precision: 93.8%, recall: 94.6%), 89.3% F1-score in severity classification, and 18.7 mm RMSE in spatial localization (R² = 0.897). The framework significantly outperformed baseline methods including SVM (6.7% improvement), Random Forest (8.9% improvement), standard LSTM (5.0% improvement), and Transformer networks (2.4% improvement), while achieving robust performance across different damage types with 97.2% detection rate for impact damage and maintaining over 80% accuracy under severe noise conditions (0 dB SNR). Ablation studies confirmed the critical contributions of attention mechanisms (2.7% improvement), bidirectional processing (5.5% improvement), and temporal convolutions (7.9% improvement). Multi-modal sensor fusion provided substantial gains over individual modalities, with AE sensors contributing 35% of the fusion weight. The deployment-optimized system achieves sub-100 millisecond inference times with robust multimodal integration, offering significant potential for industrial implementation in aerospace, civil infrastructure, and advanced manufacturing applications that require continuous structural integrity assessment.
Keywords
Structural Health Monitoring, Smart Materials, Deep Learning, Temporal Networks, Damage Detection, Multi-Modal Sensing, Carbon Fiber Composites, Real-Time Diagnostics.
L. B. Carani, J. Humphrey, M. M. Rahman, and O. I. Okoli, “Advances in Embedded Sensor Technologies for Impact Monitoring in Composite Structures,” Journal of Composites Science, vol. 8, no. 6, p. 201, May 2024, doi: 10.3390/jcs8060201.
C. Lopes et al., “Smart Carbon Fiber-Reinforced Polymer Composites for Damage Sensing and On-Line Structural Health Monitoring Applications,” Polymers, vol. 16, no. 19, p. 2698, Sep. 2024, doi: 10.3390/polym16192698.
Azadeh Keshtgar and Mohammad Modarres, “Fatigue Crack Initiation Sizing Using Acoustic Emission,” Journal of Civil Engineering and Architecture, vol. 11, no. 12, Dec. 2017, doi: 10.17265/1934-7359/2017.12.006.
A. Gomez-Cabrera and P. J. Escamilla-Ambrosio, “Review of Machine-Learning Techniques Applied to Structural Health Monitoring Systems for Building and Bridge Structures,” Applied Sciences, vol. 12, no. 21, p. 10754, Oct. 2022, doi: 10.3390/app122110754.
A. E. S. M. Atia, M. Vafaei, K. F. Tee, and S. C. Aliah, “A Systematic Review of Structural Health Monitoring Using Artificial Neural Networks: From Traditional Neural Networks to Deep Learning Algorithms.,” Dec. 2024, doi: 10.21203/rs.3.rs-5697583/v1.
M. Azimi, A. Eslamlou, and G. Pekcan, “Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review,” Sensors, vol. 20, no. 10, p. 2778, May 2020, doi: 10.3390/s20102778.
A. Mishra, G. Gangisetti, & D. Khazanchi, “Integrating edge-AI in structural health monitoring domain” 2023, arXiv preprint arXiv:2304.03718.
A. Moallemi, A. Burrello, D. Brunelli, and L. Benini, “Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring,” IEEE Internet of Things Journal, vol. 9, no. 18, pp. 17660–17674, Sep. 2022, doi: 10.1109/jiot.2022.3157532.
H. Yu, & Y. Chen, “Synergistic signal denoising for multimodal time series of structure vibration using attention-enhanced deep recurrent networks”, 2023, arXiv preprint arXiv:2308.11644. https://arxiv.org/abs/2308.11644.
X. Zhou, T. Li, Q. Zhang, & C. Jiang, “Transferring self-supervised pre-trained models for SHM anomaly detection under label scarcity”, 2024, arXiv preprint arXiv:2412.03880. https://arxiv.org/abs/2412.03880.
Y. Wei et al., “Structural health monitoring and evaluation method for an immersed tunnel based on deep learning,” Scientific Reports, vol. 15, no. 1, Jul. 2025, doi: 10.1038/s41598-025-10643-5.
T. Bao, Y. Wang, & H. Sun, “Deep transfer learning network for structural condition identification with limited real-world data” 2023, arXiv preprint arXiv:2307.15249. https://arxiv.org/abs/2307.15249.
J. Jia and Y. Li, “Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends,” Sensors, vol. 23, no. 21, p. 8824, Oct. 2023, doi: 10.3390/s23218824.
C. Tuloup, W. Harizi, Z. Aboura, Y. Meyer, K. Khellil, and R. Lachat, “On the use of in-situ piezoelectric sensors for the manufacturing and structural health monitoring of polymer-matrix composites: A literature review,” Composite Structures, vol. 215, pp. 127–149, May 2019, doi: 10.1016/j.compstruct.2019.02.046.
X. Chen et al., “In-situ damage self-monitoring of fiber-reinforced composite by integrating self-powered ZnO nanowires decorated carbon fabric,” Composites Part B: Engineering, vol. 248, p. 110368, Jan. 2023, doi: 10.1016/j.compositesb.2022.110368.
A. Coles, B. A. de Castro, C. Andreades, F. G. Baptista, M. Meo, and F. Ciampa, “Impact Localization in Composites Using Time Reversal, Embedded PZT Transducers, and Topological Algorithms,” Frontiers in Built Environment, vol. 6, Mar. 2020, doi: 10.3389/fbuil.2020.00027.
H. Su, M. Drissi-Habti, and V. Carvelli, “New Concept of Dual-Sinusoid Distributed Fiber-Optic Sensors Antiphase-Placed for the SHM of Smart Composite Structures for Offshore,” Applied Sciences, vol. 14, no. 2, p. 932, Jan. 2024, doi: 10.3390/app14020932.
J. M. Gilbert, K. Bhavsar, and O. V. Ivanov, “Robustness of embedded fibre optic sensor mesh configurations for monitoring composite structures,” Sensors and Actuators A: Physical, vol. 373, p. 115445, Aug. 2024, doi: 10.1016/j.sna.2024.115445.
M. A. Shohag, T. Ndebele, D. Olawale, And O. Okoli, “Advances of Bio-inspired In-situ Triboluminescent Optical Fiber Sensor for Damage and Load Monitoring in Multifunctional Composite,” Structural Health Monitoring 2017, Sep. 2017, doi: 10.12783/shm2017/14065.
M. A. SHOHAG, G. R. ADAMS, V. O. EZE, T. ICHITE, L. B. CARANI, and O. OKOLI, “Mechanoluminescent-Perovskite Pressure Sensor for Structural Health Monitoring,” Structural Health Monitoring 2019, Nov. 2019, doi: 10.12783/shm2019/32233.
Y. Wan et al., “Low-velocity impact damage localization of GF/epoxy laminates by the embedded MWCNT@GF sensor network,” Journal of Materials Research and Technology, vol. 9, no. 4, pp. 9253–9261, Jul. 2020, doi: 10.1016/j.jmrt.2020.06.032.
F. Hao et al., “Carbon-Nanotube-Film-Based Electrical Impedance Tomography for Structural Damage Detection of Carbon-Fiber-Reinforced Composites,” ACS Applied Nano Materials, vol. 4, no. 5, pp. 5590–5597, May 2021, doi: 10.1021/acsanm.1c01132.
K. S. C. Kuang, R. Kenny, M. P. Whelan, W. J. Cantwell, and P. R. Chalker, “Embedded fibre Bragg grating sensors in advanced composite materials,” Composites Science and Technology, vol. 61, no. 10, pp. 1379–1387, Aug. 2001, doi: 10.1016/s0266-3538(01)00037-9.
H. Kwon, Y. Park, C. Shin, J.-H. Kim, and C.-G. Kim, “Embedded silicon carbide fiber sensor network based low-velocity impact localization of composite structures,” Smart Materials and Structures, vol. 29, no. 5, p. 055030, Apr. 2020, doi: 10.1088/1361-665x/ab7946.
C. C. Bowland, N. A. Nguyen, and A. K. Naskar, “Roll-to-Roll Processing of Silicon Carbide Nanoparticle-Deposited Carbon Fiber for Multifunctional Composites,” ACS Applied Materials & Interfaces, vol. 10, no. 31, pp. 26576–26585, Jul. 2018, doi: 10.1021/acsami.8b03401.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Mithra C, Rajkumar N, Tamilarasi M, Lakshmi Prasanna, Pari R and Kalai Selvi D M;
Methodology: Mithra C, Rajkumar N and Tamilarasi M;
Writing- Original Draft Preparation: Mithra C, Rajkumar N, Tamilarasi M, Lakshmi Prasanna, Pari R and Kalai Selvi D M;
Visualization: Mithra C, Rajkumar N and Tamilarasi M;
Investigation: Lakshmi Prasanna, Pari R and Kalai Selvi D M;
Supervision: Mithra C, Rajkumar N and Tamilarasi M;
Validation: Lakshmi Prasanna, Pari R and Kalai Selvi D M;
Writing- Reviewing and Editing: Mithra C, Rajkumar N, Tamilarasi M, Lakshmi Prasanna, Pari R and Kalai Selvi D M;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Authors thank Reviewers for taking the time and effort necessary to review the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Mithra C
Department of Computational Intelligence, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Mithra C, Rajkumar N, Tamilarasi M, Lakshmi Prasanna, Pari R and Kalai Selvi D M, “Artificial Intelligence based Augmented Structural Health Monitoring in Smart Materials Using Deep Temporal Learning Networks”, Journal of Machine and Computing, vol.6, no.1, pp. 073-092, 2026, doi: 10.53759/7669/jmc202606007.
