Sanjeev Kumar,
P. Girish,
Pranashi Chakraborty,
Narne Sravanthi,
V. Akilandeswari,
Mohit Ghai,
- Professor, Department of Electronics & Communication Engineering, Aditya University, Surampalem, Andhra Pradesh, India
- Assistant Professor, Department of Civil Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, Karnataka, India
- Assistant Professor, Department of Computer Science and Engineering – AI, Brainware University, Barasat, West Bengal, India
- Assistant Professor, Department of Computer Science and Engineering, Velammal College of Engineering and Technology, Madurai, Andhra Pradesh, India
- Associate Professor, Department of Computer Science and Engineering, Velammal College of Engineering and Technology, Madurai, Tamil Nadu, India
- Assistant Professor, Department of Computer Science, Guru Gobind Singh Indraprastha University, New Delhi, India
Abstract
This study developed an embedded Internet of Things sensor network for real-time crack detection, localization, and severity assessment in glass–fiber-reinforced polymer composites. Four polyvinylidene fluoride sensors were embedded near the laminate mid-plane and connected to synchronized wireless acquisition nodes. Controlled low-velocity impacts generated graded damage states. Ultrasonic C-scan and optical microscopy provided independent labels. A compact multi-channel convolutional model processed normalized waveforms, spectral entropy, signal energy, and arrival-time differences at an edge gateway. The framework achieved a macro-F1 score of 0.938, a mean localization error of 8.9 mm, and an average end-to-end warning latency of 71 ms. Sensor-embedded laminates retained 99.1% of the flexural strength of uninstrumented controls. Multi-sensor fusion and baseline normalization produced the largest reductions in false alarms. The approach also preserved records during temporary wireless interruption through local buffering. The proposed material-aware IoT architecture allows for fast crack monitoring. It offers spatially-distributed detection of structural damage. This system can be used for continuous monitoring of polymer composites. It identifies cracks at an early stage. There are no major mechanical penalties to the architecture. It maintains the structural performance of the composite. This allows for condition-based maintenance to be performed. Overall, it enhances the reliability and service life of polymer–composite structures.
Keywords: Polymer composites, crack detection, embedded sensors, internet of things, structural health monitoring.
[This article belongs to Special Issue under section in Journal of Polymer & Composites (jopc)]
References
1. Yuan W, Zhang Z, Li Y, Huang Y, Zhong Z, Hu Z. Self-healing and in-situ real-time damage-reporting fiber-reinforced composite. Compos Sci Technol. 2024;245:110344.
2. Lu L, Hou J, Yuan S, Yao X, Li Y, Zhu J. Deep learning-assisted real-time defect detection and closed-loop adjustment for additive manufacturing of continuous fiber-reinforced polymer composites. Robot Comput Integr Manuf. 2023;79:102431.
3. Yu Y, Liu X, Cui X, Wang Y, Qing X. In-situ cure monitoring of thick CFRP using multifunctional piezoelectric-fiber hybrid sensor network. Compos Sci Technol. 2023;240:110079.
4. Mamodiya U, Kishor I, Vidyullatha P, Alqutaesh A, Alradwan G, Obedat M. A hybrid fuzzy–deep learning framework for real-time cyber-attack detection in smart energy grids. Int J Data Netw Sci. 2026;10.
5. Preto E, Ambrozini B, da Silva S, Orlandi MO. Nanocomposite sensors with indium tin oxide nanowires in a polyvinyl butyral matrix for crack detection in structural health monitoring. Struct Health Monit. 2026;25(4):2628–42.
6. Malik S, Kontsos A. A novel information entropy approach for crack monitoring leveraging nondestructive evaluation sensing. Mech Syst Signal Process. 2024;214:111207.
7. Yu Z, Sun J, Yue M, Xu C. Accelerated strategies for impact identification of composite laminate using sparse sensor networks and model-based virtual time reversal. Struct Health Monit. 2026;25
(1):174–95.
8. Mamodiya U, Kishor I. A novel framework for smart agriculture: Integrating deep learning and blockchain for precision farming. In: AI and green technology applications in society 2025. IGI Global Scientific Publishing; 2025. p. 123–144.
9. Cui X, Yu Y, Liu Q, Liu X, Qing X. Full-field monitoring of the resin flow front and dry spot with noninvasive and embedded piezoelectric sensor networks. Smart Mater Struct. 2023;32(8):
085021. doi: 10.1088/1361-665X/ace296.
10. Li Z, Sun C, Guo S, Zhang Z, Wang T. Embedding PVDF sensors in CFRP without compromise: PCL encapsulation for simultaneous damage detection and interlayer toughening. Polym Compos. 2026;47(10):9337–9351. doi: 10.1002/pc.70762.
11. Xu G, Yue Q, Liu X. Deep learning algorithm for real-time automatic crack detection, segmentation, qualification. Eng Appl Artif Intell. 2023;126:107085.
12. Ghazali M, Karamooz Mahdiabadi M. High-precision multiple defect detection and localization in composite laminates using integrated piezoelectric sensing, regression and neural networks methods. Sci Rep. 2025;15(1):35681.
13. Gantla HR, Namdev M, Mamodiya U, Kishor I, Kumar G, Goyal P. A Smart Monitoring Framework for Sustainable Solar Energy Harvesting Using IoT and Machine Learning Techniques. In: 2025 International Conference on Sustainability, Innovation & Technology (ICSIT); 2025 Aug 22. IEEE. p. 1–6.
14. Quqa S, Landi L, Loh KJ. Crack identification using electrical impedance tomography and transfer learning. Comput Aided Civ Infrastruct Eng. 2023;38(17):2426–2442. doi: 10.1111/mice.13043.
15. Qin H, Yang Y, Sun M, Zhu J, Liu S, Sun H, et al. Monitoring of Mixed Failure Mode in CFRP Bolted Joint Structures Based on a Modular Piezoresistive Sensing Network. Polym Compos. 2026;47(7):6144–57.
16. Kishor I, Mamodiya U, Sharma M, Kumar G, Goyal P. Integrating Block Chain with IoT for Secure and Transparent Supply Chain Management in Sustainable Manufacturing. In: 2025 International Conference on Sustainability, Innovation & Technology (ICSIT); 2025 Aug 22. IEEE. p. 1–6.
17. Ahn JH, Lee YC, Jeong SM, Kim HN, Lee CY. Crack detecting method based on grid-type sensing networks using electrical signals. Sensors. 2023;23(13):6093. doi: 10.3390/s23136093.
18. Zhang F, Gong L, Wang F, Zhou H, He W, Huang Z, et al. Embedded Pt-PVDF sensor without compromising mechanical properties of GFRP for on-line sensing. Thin-Walled Struct. 2023;187:110702.
19. Batista GC, Zetterling CM, Öberg J, Saotome O. SHM system for composite material based on Lamb waves and using machine learning on hardware. Sensors. 2024;24(23):7817. doi: 10.3390/
s24237817.
20. Herry G, Fustec JC, Le Bihan F, Harnois M. Substrate-free transfer of silicon- and metallic-based strain sensors on textile and in composite material for structural health monitoring. ACS Appl Mater Interfaces. 2024;16(17):22113–22121. doi: 10.1021/acsami.4c01055.
21. Shi J, Kong D, Li C, Guo R, Xian G, Liu H, et al. Strain and damage monitoring of optical fiber sensor-embedded carbon fiber reinforced polymer confined cracked pipes. Polym Compos. 2025;46(6):5419–38.
22. Mamodiya U, Kishor I, Vidyullatha P, Almaayah M, Routray A. A bio-inspired neuro-adaptive deep reinforcement learning approach for real-time solar tracking system to enhance photovoltaic efficiency. Energy Convers Manag X. 2025:101486.
23. Chen K, Bao T, Yang H, Dong Y, Di Y, Wang X, et al. In-situ graft fibrous PPy@PEI enables sensitive and all-seasoned crack monitoring for ancient architectures based on flexible pressure sensors. Chem Eng J. 2024;491:151746.
24. Wang W, Zhang B, Feng H, Wei Z, Dai Z, Zhang H, et al. A three-dimensional surface-adaptive stretchable sensor for online monitoring of composite materials curing. ACS Sens. 2024;9(11):6174–6184. doi: 10.1021/acssensors.4c02022.
25. Miyashita T, Katabira K, Kurita H, Nakaki T, Narita F. Crack self-sensing capability of glass fiber reinforced polymer composites embedded with magnetostrictive fibers in mixed-mode bending. Compos Sci Technol. 2023;241:110107.
26. Shah Mansouri T, Lubarsky G, Finlay D, McLaughlin J. Machine learning-based structural health monitoring technique for crack detection and localisation using Bluetooth strain gauge sensor network. J Sens Actuator Netw. 2024;13(6):79. doi: 10.3390/jsan13060079.
27. Alblalaihid KS, Aldoihi SA, Alharbi AA. Structural health monitoring of fiber reinforced composites using integrated a linear capacitance based sensor. Polymers. 2024;16(11):1560. doi: 10.3390/polym16111560.
28. Yu Y, Kubota Y, Kurita H, Narita F. Piezoelectric glass-fiber-reinforced polymer sensor for structural health monitoring and stiffness sensing. Adv Eng Mater. 2023;25(20):2300638.
29. Barragán J, Kell A, Liu X, Shin S, Mandache C, Djokic D, et al. Next-generation embedded printed sensors for near-field monitoring of high-performance composites. Adv Eng Mater. 2025;27(4):2401332.
30. Liu Q, Sun M, Qin H, Wang K, Sun H, Wang Y, et al. Embedded piezoresistive sensor network for multi-failure mode monitoring in CFRP bolted joints. IEEE Sens J. 2024;25(2):3490–502.
31. Jung YJ, Jang SH. Crack detection of reinforced concrete structure using smart skin. Nanomaterials. 2024;14(7):632. doi: 10.3390/nano14070632.
32. Yu MH, Lee JS, Kim HS. Machine learning-based damage sensing and self-healing of carbon fiber/nylon composites via addressable conducting networks. Struct Health Monit. 2023;22(5):
3401–3415. doi: 10.1177/14759217221141764.
33. Wang Y, Qiu L, Zheng H, Xu Q. Digitalized global impact localization for complex composites based on wireless PZT sensor network. IEEE Trans Instrum Meas. 2022;72:1–0.
34. Gaben M, Goldfeld Y. Locating cracks in smart TRC elements based on the TDR concept. Struct Health Monit. 2024;23(5):2698–2712. doi: 10.1177/14759217231210508.
35. Wang HP, Chen C, Ni YQ, Jayawickrema M, Epaarachchi J. Computer-aided feature recognition of CFRP plates based on real-time strain fields reflected from FBG measured signals. Compos B Eng. 2023;263:110866.
Journal of Polymer & Composites
| Volume | 14 | |
| Special Issue | 04 | |
| Received | 24/07/2026 | |
| Accepted | 13/08/2026 | |
| Published | 20/08/2026 | |
| Publication Time | 27 Days |