ML-Enhanced Smart Sensing Framework for IoT- Based Structural Health Monitoring Using Conductive Polymer Composites

Year : 2025 | Volume : 13 | Special Issue 06 | Page : 348 369
    By

    Nagaraj G.,

  • Amaravarapu Pramod Kumar,

  • Basavaraju Kachapuram,

  • Muthukumar Subramanian,

  • Ashish Avasthi,

  • Gandikota Dhana Lakshmi,

  1. Associate Professor, Department of Mechanical Enigneering , Sethu Institute of Technology, Tamil Nadu, India
  2. Assistant Professor, Department of Computer Science and Engineering – Data Science, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering &Technology, Hyderabad, Telangana, India
  3. Associate Professor, Department of Artificial Intelligence, Anurag University, Majarguda, Telangana, India
  4. Professor, Department of Computer Science and Engineering, Hindustan Institute of Technology & Science (Deemed to be University), New Delhi, India
  5. Professor, Department of Computer Science and Engineering, Poornima University, Jaipur, Rajasthan, India
  6. Assistant Professor, Department of Mathematics and Statistics, Vignan’s Foundation for Science, Technology & Research (Deemed to be University), Guntur, Andhra Pradesh, India

Abstract

The growing demand for intelligent structural health monitoring (SHM) in dynamic infrastructures necessitates flexible sensing systems that are not only mechanically robust but also capable of real-time interpretation. Conventional SHM frameworks often rely on brittle sensor configurations and cloud-dependent processing pipelines, which suffer from latency, limited durability, and poor adaptability under variable loading conditions. Despite recent advances in composite materials and machine learning, current approaches lack a unified framework that seamlessly integrates material-level sensitivity with embedded predictive intelligence. To address this limitation, we propose CPC-Net, a novel fabrication-to-inference pipeline combining piezoresistive polymer composites with an edge-deployable hybrid CNN-LSTM model. The composite is engineered with graphene-reinforced elastomer matrices to ensure high gauge sensitivity and repeatable electromechanical behavior under cyclic strain. A dedicated embedded architecture supports in-situ signal preprocessing, real-time ML inference, and adaptive calibration, optimized for constrained IoT environments. The proposed system achieved an R² of 0.984 in strain-resistance prediction, with a gauge factor (GF) between 8–12. Machine learning inference yielded an accuracy of 93.4%, an F1-score of 0.91, and inference latency of 41 ms, outperforming existing SHM baselines across all tested metrics. This integrated solution demonstrates strong potential for deployment in next-generation SHM applications, offering a scalable, low-latency, and mechanically resilient alternative for real-time monitoring of civil infrastructure, soft robotics, and biomechanical systems.

Keywords: Structural health monitoring, piezoresistive composites, embedded machine learning, flexible sensors, CNN-LSTM inference.

[This article belongs to Special Issue under section in Journal of Polymer and Composites (jopc)]

How to cite this article:
Nagaraj G., Amaravarapu Pramod Kumar, Basavaraju Kachapuram, Muthukumar Subramanian, Ashish Avasthi, Gandikota Dhana Lakshmi. ML-Enhanced Smart Sensing Framework for IoT- Based Structural Health Monitoring Using Conductive Polymer Composites. Journal of Polymer and Composites. 2025; 13(06):348-369.
How to cite this URL:
Nagaraj G., Amaravarapu Pramod Kumar, Basavaraju Kachapuram, Muthukumar Subramanian, Ashish Avasthi, Gandikota Dhana Lakshmi. ML-Enhanced Smart Sensing Framework for IoT- Based Structural Health Monitoring Using Conductive Polymer Composites. Journal of Polymer and Composites. 2025; 13(06):348-369. Available from: https://journals.stmjournals.com/jopc/article=2025/view=230344


Browse Figures

References

  1. S. Attar, A. Makandar, M. Ziaullah, and S. Fatima, “IoT-Machine Learning-Based Structural Health Monitoring System for Detection of Cracks in Bridges,” Saudi journal of biomedical research, Mar. 2024, doi: 10.36348/sjbr.2024.v09i02.001.
  2. Karuppusamy, R. Thirumalaisamy, S. Palanisamy, S. Nagamalai, E. E. S. Massoud, and N. Ayrilmis, “A review of machine learning applications in polymer composites: advancements, challenges, and future prospects,” J. Mater. Chem. A, vol. 13, pp. 16290–16308, 2025, doi: 10.1039/D5TA00982K.
  3. Karuppusamy, S. Kalidas, S. Palanisamy, K. Nataraj, R. K. Nandagopal, R. Natarajan, A. Samraj, N. Ayrilmis, S. K. Sahu, J. Giri, and M. Kanan, “Real‑time monitoring in polymer composites: Internet of things integration for enhanced performance and sustainability — A Review,” BioResources, vol. 20, no. 3, 2025, doi: 10.15376/biores.20.3.Karuppusamy
  4. H. Taymaz, H. Kamış, M. Dziendzikowski, et al., “Enhancing structural health monitoring of fiber-reinforced polymer composites using piezoresistive Ti₃C₂Tₓ MXene fibers,” Scientific Reports, vol. 15, p. 2456, 2025, doi: 10.1038/s41598-024-78338-x.
  5. Pop et al., “A Machine Learning-Driven Wireless System for Structural Health Monitoring,” INCAS Buletin, Sep. 2024, doi: 10.13111/2066-8201.2024.16.3.8.
  6. State Space Emulation and Annealed Sequential Monte Carlo for High Dimensional Optimization,” Statistica Sinica, Jan. 2025, doi: 10.5705/ss.202022.0120
  7. S. Mansouri, G. Lubarsky, D. Finlay, and J. McLaughlin, “Machine learning-based structural health monitoring technique for crack detection and localisation using Bluetooth strain gauge sensor network,” Journal of Sensor and Actuator Networks, vol. 13, no. 6, p. 79, Nov. 2024, doi: 10.3390/jsan13060079.
  8. Adam, M. Lambat, and P. Kraemer, “Robust Structural Health Monitoring of CFRP Structures under Varying Loads using NSFD and Machine Learning with Combined Usage of Acceleration and Strain Data,” E-Journal of nondestructive testing, vol. 29, no. 7, Jul. 2024, doi: 10.58286/29841.
  9. Mhanna, M., Rochussen, J., & Kirchen, P. (2025). An ML-Enhanced Laser-Based Methane Slip Sensor Using Wavelength Modulation Spectroscopy. ACS Sensors. https://doi.org/10.1021/acssensors.4c02374
  10. Ye, C., Lukas, H., Wang, M., Lee, Y., and Gao, W., “Molecularly imprinted polymer-based wearable biosensors,” Chem. Soc. Rev., vol. 53, pp. 7960–7982, 2024.
  11. K. Paul, R. Pasupathy, V. Mariyappan, D. Ravichandran, and J. Marimuthusamy, “IoT based patient health monitoring system with smart health care box,” Nucleation and Atmospheric Aerosols, vol. 3159, p. 030002, Jan. 2025, doi: 10.1063/5.0247949.
  12. Shah Mansouri, G. Lubarsky, D. Finlay, and J. McLaughlin, “Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network,” Sep. 2024, doi: 10.20944/preprints202409.1639.v1.
  13. Chew, A. K., Afzal, M. A. F., Chandrasekaran, A., Kamps, J. H., & Ramakrishnan, V. (2024). Designing the Next Generation of Polymers with Machine Learning and Physics-Based Models. Machine Learning: Science and Technology. https://doi.org/10.1088/2632-2153/ad88d7
  14. Hu, H., Wei, Q., Wang, T., Ma, Q., Jin, P., Pan, S., Li, F., Wang, S., Yang, Y., & Li, Y. (2024). Experimental and Numerical Investigation Integrated with Machine Learning (ML) for the Prediction Strategy of DP590/CFRP Composite Laminates. Polymers, 16(11), 1589. https://doi.org/10.3390/polym16111589
  15. T. Vo, S. R. Padma, E. C. Ngin, V. S. Shankar, H. Li, and S. Idapalapati, “Feasibility of in-situ health monitoring for composite structure with embedded piezoelectric sensor networks,” Feb. 2024, doi: 10.1117/12.3022258.
  16. Amelia, S., Sabila, L. Y., Jamilatun, S., & Mufandi, I. (2025). Iot-Driven Smart Waste Management for Sustainable Dye Removal in Batik Industry Effluents Using Biochar and Zeolite-Based Heterogeneous Fenton Processes. https://doi.org/10.2139/ssrn.5078657
  17. K. Paul, R. Pasupathy, V. Mariyappan, D. Ravichandran, and J. Marimuthusamy, “IoT based patient health monitoring system with smart health care box,” Nucleation and Atmospheric Aerosols, vol. 3159, p. 030002, Jan. 2025, doi: 10.1063/5.0247949.
  18. Dolińska, G. Wojciechowska, and Ł. Bednarz, “Monitoring Environmental and Structural Parameters in Historical Masonry Buildings Using IoT LoRaWAN-Based Wireless Sensors,” Buildings, vol. 15, no. 2, p. 282, Jan. 2025, doi: 10.3390/buildings15020282.
  19. Qi, “Advancing hospital healthcare: achieving IoT-based secure health monitoring through multilayer machine learning,” Journal of Big Data, vol. 12, no. 1, Jan. 2025, doi: 10.1186/s40537-024-01038-w.
  20. Shah Mansouri, G. Lubarsky, D. Finlay, and J. McLaughlin, “Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network,” Journal of Sensor and Actuator Networks, vol. 13, no. 6, p. 79, Nov. 2024, doi: 10.3390/jsan13060079.
  21. Haspulat Taymaz, H. Kamış, M. Dziendzikowski, K. Kowalczyk, K. Dragan, and V. Eskizeybek, “Enhancing structural health monitoring of fiber-reinforced polymer composites using piezoresistive Ti3C2Tx MXene fibers,” Dental science reports, vol. 15, no. 1, Jan. 2025, doi: 10.1038/s41598-024-78338-x.
  22. Najem, M. Benbrahim, M. N. Kabbaj, and J. Boumhidi, “Synergy between Embedded and Non-Embedded Sensors in IoT Networks for Structural Health Monitoring of Concrete Structures: A Literature Review,” E3S web of conferences, vol. 601, p. 00028, Jan. 2025, doi: 10.1051/e3sconf/202560100028.
  23. Rajasekhar and M. Z. Khan, “Structural Health Monitoring Using IOT,” Indian Scientific Journal Of Research In Engineering And Management, vol. 08, no. 07, pp. 1–14, Jul. 2024, doi: 10.55041/ijsrem36802.
  24. Arif, L. Ayub, F. Khan, and A.-R. Khan, “Conceptual Framework for IoT-Based Structural Health Monitoring of RC Bridges for Maintenance Decision-Making,” Construction technologies and architecture, vol. 15, pp. 19–26, Jan. 2025, doi: 10.4028/p-q8nkqw.
  25. Forlesi et al., “An IoT-AI Toolchain for Structural Health Monitoring,” pp. 1–6, Jul. 2024, doi: 10.1109/mn60932.2024.10615472.
Special Issue Subscription Original Research
Volume 13
Special Issue 06
Received 31/07/2025
Accepted 18/08/2025
Published 09/09/2025
Publication Time 40 Days
17


My IP

PlumX Metrics