This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Ekta Singh,
Rupesh Kumar,
Galla Damodara Krishna Kishore,
Gogineni Krishna Chaitanya,
D. Naga Malleswari,
D. Gouse Peera,
- Assistant Professor, Department of Commerce, University School of Business, Chandigarh University, Mohali, Punjab, India
- Assistant Professor, Department of Law, Maharishi Markandeshwar (Deemed to be University), Mullana, Ambala, Haryana, India
- Associate Professor, Department of Compute Science and Engineering (AI&ML), R.V.R. & J.C. College of Engineering, Chowdavaram, Guntur, Andhra Pradesh, India
- Associate Professor, Department of Compute Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfields, Vaddeswaram, Guntur, Andhra Pradesh, India
- Associate Professor, Department of Compute Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfields, Vaddeswaram, Guntur, Andhra Pradesh, India
- Assistant Professor, Department of Civil Engineering, Annamacharya University, Rajampet, Andhra Pradesh, India
Abstract
Damage assessment of carbon-fibre-reinforced polymer composites is still challenging since the damage occurs as a combination of matrix cracking, interfacial debonding, delamination and fibre fracture. The present work proposes a framework for predictive-intelligence based on IoT for multiaxial fatigue and compression-after-impact (CAI) CFRP experiments, employing publicly available acoustic-emission (AE) datasets. A causal CNN–GRU attention model is developed by integrating time-domain, spectral, wavelet, loading-history and trend features to estimate the damage evolution, imminent failure and normalized remaining life. To avoid leakage and to test robustness, specimen-level splitting, training-only normalization, five-seed evaluation and independent cross domain validation were used. The framework was evaluated on held-out fatigue specimens, and yielded a damage-estimation R² of 0.946, RMSE of 0.052, failure-prediction AUROC of 0.967, F1-score of 0.918, and remaining-life MAE of 0.071. External validation showed R² of 0.889 and AUROC of 0.912 and real-time replay had mean latency of 28.6 ms. The predicted critical transition also remained close to the independently reported unstable damage region, indicating useful transfer across distinct loading conditions. The results show that temporally resolved AE monitoring can support early warning and continuous structural-health assessment of polymer composites, providing a practical bridge between sensing, prognosis, and IoT-enabled condition-based maintenance.
Keywords: Damage assessment of carbon-fibre-reinforced polymer composites is still challenging since the damage occurs as a combination of matrix cracking, interfacial debonding, delamination and fibre fracture. The present work proposes a framework for predictive-intelligence based on IoT for multiaxial fatigue and compression-after-impact (CAI) CFRP experiments, employing publicly available acoustic-emission (AE) datasets. A causal CNN–GRU attention model is developed by integrating time-domain, spectral, wavelet, loading-history and trend features to estimate the damage evolution, imminent failure and normalized remaining life. To avoid leakage and to test robustness, specimen-level splitting, training-only normalization, five-seed evaluation and independent cross domain validation were used. The framework was evaluated on held-out fatigue specimens, and yielded a damage-estimation R² of 0.946, RMSE of 0.052, failure-prediction AUROC of 0.967, F1-score of 0.918, and remaining-life MAE of 0.071. External validation showed R² of 0.889 and AUROC of 0.912 and real-time replay had mean latency of 28.6 ms. The predicted critical transition also remained close to the independently reported unstable damage region, indicating useful transfer across distinct loading conditions. The results show that temporally resolved AE monitoring can support early warning and continuous structural-health assessment of polymer composites, providing a practical bridge between sensing, prognosis, and IoT-enabled condition-based maintenance.
References
[1]. Q. Li, Z. Liu, D. Ji, et al., “A data-driven framework for real-time failure prediction in adhesively bonded composite joint with acoustic emission data,” Thin-Walled Structures, vol. 222, Art. no. 114489, 2026, doi: 10.1016/j.tws.2026.114489.
[2]. J. Du, P. Hao, J. Cui, and H. Wang, “Dual-branch parallel CNN-Transformer-LSTM framework and transfer learning for real-time structural health monitoring of CFRP composite,” Composites Part B: Engineering, vol. 325, Art. no. 113996, 2026, doi: 10.1016/j.compositesb.2026.113996.
[3]. S. Zhang, H. Li, D. Sun, et al., “AE-driven machine learning framework for CFRP damage mode identification and energy-based damage assessment,” Composite Structures, vol. 389, Art. no. 120439, 2026, doi: 10.1016/j.compstruct.2026.120439.
[4]. U. Mamodiya et al., “A Bio-Inspired Neuro-Adaptive Deep Reinforcement Learning Approach for Real-Time Solar Tracking System to Enhance Photovoltaic Efficiency,” Energy Conversion and Management: X, 2026.
[5]. A. Vahid Movahedi-Rad and T. Keller, “Load history effects in fiber–polymer composites: A CRNN-based hybrid deep learning approach for fatigue life prediction and structural health monitoring via infrared thermography,” Composites Part A: Applied Science and Manufacturing, vol. 200, Art. no. 109263, 2026, doi: 10.1016/j.compositesa.2025.109263.
[6]. J. Du, J. Zeng, C. Chen, et al., “Acoustic emission monitoring for damage diagnosis in composite laminates based on deep learning with attention mechanism,” Mechanical Systems and Signal Processing, vol. 222, Art. no. 111770, 2025, doi: 10.1016/j.ymssp.2024.111770.
[7]. Y. S. Krishna, G. Raju, and M. S. Desarkar, “Damage characterization of CFRP composites under compression using acoustic emission time–frequency analysis and unsupervised deep learning,” Mechanical Systems and Signal Processing, vol. 238, Art. no. 113224, 2025, doi: 10.1016/j.ymssp.2025.113224.
[8]. R. Garine, et al., “Artificial Intelligence Based Hybrid Solar Energy Systems With Smart Materials and Adaptive Photovoltaics for Sustainable Power Generation,” Scientific Reports, 2025.
[9]. C. Barile, C. Casavola, G. Pappalettera, and V. P. Kannan, “Investigation of an improved time of arrival detection method for acoustic emission signals and its applications to damage characterisation in composite materials,” Mechanical Systems and Signal Processing, vol. 223, Art. no. 111906, 2025, doi: 10.1016/j.ymssp.2024.111906.
[10]. C. Liu, Y. Chen, and X. Xu, “Structural digital twin for damage detection of CFRP composites using meta transfer learning-based approach,” Expert Systems with Applications, vol. 261, Art. no. 125458, 2025, doi: 10.1016/j.eswa.2024.125458.
[11]. X. Xiong, Y. Zhang, Y. Zhang, and Z. Luo, “FBG sensing fusion with deep learning for damage identification in CFRP composites,” Optical Fiber Technology, vol. 93, Art. no. 104256, 2025, doi: 10.1016/j.yofte.2025.104256.
[12]. U. Mamodiya et al., “A Hybrid Machine Learning Framework for Predictive Maintenance in Renewable Energy Systems to Enhance Efficiency and Longevity,” ICSIT 2025.
[13]. G. Jovarauskaite, G. Monastyreckis, L. Mishnaevsky Jr., and D. Zeleniakiene, “Self-sensing composites with damage mapping using 3D carbon fibre grid,” Composites Part B: Engineering, vol. 295, Art. no. 112182, 2025, doi: 10.1016/j.compositesb.2025.112182.
[14]. R. K. Langat, W. Deng, E. De Luycker, A. Cantarel, and M. Rakotondrabe, “In-situ piezoelectric sensors for structural health monitoring with machine learning integration,” Mechatronics, vol. 106, Art. no. 103297, 2025, doi: 10.1016/j.mechatronics.2025.103297.
[15]. A. Al-Nadhari, C. Yildirim, S. Topal, I. E. Tabrizi, and M. Yildiz, “In-situ acoustic emission based technique for damage detection and identification and failure mode prediction in scarf repaired composite structures,” Measurement, vol. 242, Art. no. 116068, 2025, doi: 10.1016/j.measurement.2024.116068.
[16]. M. Smolnicki, S. Duda, P. Zielonka, and P. Stabla, “Damage characterisation of GFRP composites based on clustering acoustic emission events utilizing single-failure-cause tests as reference,” Composite Structures, vol. 351, Art. no. 118596, 2025, doi: 10.1016/j.compstruct.2024.118596.
[17]. H. R. Gantla, M. Namdev, U. Mamodiya, I. Kishor, G. Kumar, and P. Goyal, “A Smart Monitoring Framework for Sustainable Solar Energy Harvesting Using IoT and Machine Learning Techniques,” in 2025 International Conference on Sustainability, Innovation & Technology (ICSIT), Nagpur, India, 2025, pp. 1–6, doi: 10.1109/ICSIT65336.2025.11295019.
[18]. Z.-J. Xu, H. Li, J.-B. Yu, and J. Yu, “Deep transfer learning for delamination damage in CFRP composite materials,” Structural Health Monitoring, vol. 25, no. 3, pp. 1699–1716, 2026, doi: 10.1177/14759217241311942.
[19]. Y. Zhang, C. Xu, P. Liu, J. Xie, Y. Han, R. Liu, and L. Chen, “One-dimensional deep convolutional autoencoder active infrared thermography: Enhanced visualization of internal defects in FRP composites,” Composites Part B: Engineering, vol. 272, Art. no. 111216, 2024, doi: 10.1016/j.compositesb.2024.111216.
[20]. C. Liu, Y. Chen, X. Xu, and W. Che, “Domain generalization-based damage detection of composite structures powered by structural digital twin,” Composites Science and Technology, vol. 258, Art. no. 110908, 2024, doi: 10.1016/j.compscitech.2024.110908.
[21]. Y. Zhang, M. Radzieński, and W. Ostachowicz, “Diagnostic-prognostic framework for assessing the health status of composite structures,” International Journal of Mechanical Sciences, vol. 278, Art. no. 109461, 2024, doi: 10.1016/j.ijmecsci.2024.109461.
[22]. W. Li et al., “FE-based machine learning model for predictive damage assessment in bonded composite joints via acoustic emission,” Composites Part A: Applied Science and Manufacturing, vol. 187, Art. no. 108494, 2024, doi: 10.1016/j.compositesa.2024.108494. (ResearchGate)
[23]. U. Mamodiya et al., “Innovative AI Techniques for Solar Energy Systems: Predictive Analytics and Real-Time Optimization,” AIP Conference Proceedings, 2026.
[24]. A. Tavares, E. Di Lorenzo, B. Cornelis, B. Peeters, W. Desmet, and K. Gryllias, “Machine learning approaches to damage detection in composite structures combining experimental and simulation domains,” Mechanical Systems and Signal Processing, vol. 215, Art. no. 111412, 2024, doi: 10.1016/j.ymssp.2024.111412.
[25]. Y. Liao, Y. Huang, Y. Wang, M. Wu, F. Zhang, and X. Qing, “Complex CFRP damage detection with dual multiscale 1DCNNs and self-selective fusion technique of guided waves,” Composite Structures, vol. 335, Art. no. 117993, 2024, doi: 10.1016/j.compstruct.2024.117993.
[26]. T. Tian, L. Yang, W. Liu, et al., “Two-stage residual networks for damage identification and location of stiffened composite panel based on guided waves,” NDT & E International, vol. 146, Art. no. 103162, 2024, doi: 10.1016/j.ndteint.2024.103162.
[27]. X. Cheng, J. Liu, K. Zheng, Z. Wu, L. Shi, and X. Hu, “Monitoring of damage evolution in carbon fiber reinforced polymer composites by electrical impedance tomography,” NDT & E International, vol. 148, Art. no. 103239, 2024, doi: 10.1016/j.ndteint.2024.103239.
[28]. Kishor et al., “An Internet of Things-Enabled Adaptive Robotic Framework for Autonomous Navigation in Smart Campus and Urban Mobility Systems,” Robotica, 2025.
[29]. Du, H. Wang, C. Chen, et al., “Damage classification and evolution in composite under low-velocity impact using acoustic emission, machine learning and wavelet packet decomposition,” Engineering Fracture Mechanics, vol. 306, Art. no. 110238, 2024, doi: 10.1016/j.engfracmech.2024.110238.
[30]. Du, J. Zeng, H. Wang, H. Ding, H. Wang, and Y. Bi, “Using acoustic emission technique for structural health monitoring of laminate composite: A novel CNN-LSTM framework,” Engineering Fracture Mechanics, vol. 309, Art. no. 110447, 2024, doi: 10.1016/j.engfracmech.2024.110447.
[31]. R. Q. Albuquerque, A. Sarhadi, M. Demleitner, H. Ruckdäschel, and M. A. Eder, “Fatigue damage reconstruction in glass/epoxy composites via thermal analysis and machine learning: A theoretical study,” Composite Structures, vol. 331, Art. no. 117855, 2024, doi: 10.1016/j.compstruct.2023.117855.
[32]. S. Duda, M. Smolnicki, P. Zielonka, P. Stabla, and G. Lesiuk, “Multiaxial fatigue behavior of CFRP thin-walled tubes: An experimental study with analysis of the acoustic signals,” Polymers, vol. 17, no. 19, Art. no. 2701, 2025, doi: 10.3390/polym17192701
[33]. S. Duda, “Fatigue behavior of CFRP thin-walled tubes: An experimental study with damage analysis based on the acoustic signals,” Zenodo, 2025, doi: 10.5281/zenodo.14776947.
[34]. D. Biagini, J.-A. Pascoe, and R. C. Alderliesten, “Acoustic Emission monitoring in CFRP compression tests,” 4TU.ResearchData, 2022, doi: 10.4121/21621381.
[35]. D. Biagini, J.-A. Pascoe, and R. Alderliesten, “Investigation of compression after impact failure in carbon fiber reinforced polymers using acoustic emission,” Journal of Composite Materials, vol. 57, no. 10, pp. 1819–1832, 2023, doi: 10.1177/00219983231163853.
[36]. A. Banks, E. Briggs, K. Borgendale, and R. Gupta, Eds., MQTT Version 5.0, OASIS Standard, Mar. 7, 2019
Journal of Polymer & Composites
| Volume | 14 | |
| 05 | ||
| Received | 07/09/2026 | |
| Accepted | 19/09/2026 | |
| Published | 22/09/2026 | |
| Publication Time | 15 Days |