International Journal of Computer Network and Information Security (IJCNIS)
IJCNIS Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1081KB)
Graph Neural Networks for Predictive Maintenance in IoT Sensor Systems Using Device Telemetry Data
PDF (1081KB), PP.182-196
Views: 0 Downloads: 0
Author(s)
M. Poonguzhali
1,*
R. Sujitha
2
A. Mahendar
3
Siva Reddy Sonti
4
Malapati Naresh
5
Anjali B. V.
6
Index Terms
Graph Neural Networks (GNN), Predictive Maintenance, Internet of Things (IoT), Dynamic Graph Learning, Remaining Useful Life (RUL) Estimation.
Abstract
Industrial IoT systems generate massive telemetry streams, requiring intelligent predictive maintenance models to detect failures early, reduce downtime, and improve operational reliability and safety. Traditional approaches employ statistical analysis, sequence segmentation techniques, CNN-LSTM hybrids, and graph-based classification models to capture spatial-temporal dependencies and identify abnormal device behaviour patterns. These methods typically achieve high classification accuracy but often exhibit moderate RUL estimation performance, demonstrating strong fault detection capability across industrial, energy, and smart infrastructure applications. However, static graph structures, limited temporal attention, imbalanced fault distributions, and poor generalization under noisy conditions restrict robustness and real-world deployment scalability. This paper proposes a dynamic graph-based GAT-BiLSTM with cross-attention and gated fusion, achieving 99.50% accuracy and superior RUL prediction stability under noisy conditions. The framework incorporates adaptive adjacency learning and multi-task optimization to enhance predictive maintenance accuracy and robustness in IoT sensor networks.
Cite This Paper
M. Poonguzhali, R. Sujitha, A. Mahendar, Siva Reddy Sonti, Malapati Naresh, Anjali B. V., "Graph Neural Networks for Predictive Maintenance in IoT Sensor Systems Using Device Telemetry Data", International Journal of Computer Network and Information Security(IJCNIS), Vol.18, No.5, pp. 182-196, 2026. DOI:10.5815/ijcnis.2026.05.11
Reference
[1]Y. Wang, M. Wu, X. Li, L. Xie, and Z. Chen, “A survey on graph neural networks for remaining useful life prediction: Methodologies, evaluation and future trends,” Mechanical Systems and Signal Processing, 2025, vol. 229, p. 112449, doi: 10.1016/j.ymssp.2025.112449.
[2]M. A. S. Sejan, M. H. Rahman, M. A. Aziz, R. Tabassum, J.-I. Baik, and H.-K. Song, “Powerful graph neural network for node classification of the IoT network,” Internet of Things, 2024, vol. 28, p. 101410, doi: 10.1016/j.iot.2024.101410.
[3]B. Magar, R. Kulkarni, V. Khatavkar, et al., “Predictive network congestion management for enterprise systems: A graph neural network approach with operational insights,” Journal of Electrical Systems and Information Technology, 2025, vol. 12, p. 92, doi: 10.1186/s43067-025-00282-1.
[4]Y. Zhong, “Collaboration of IoT devices in smart home scenarios: Algorithm research based on graph neural networks and federated learning,” Discover Internet of Things, 2025, vol. 5, p. 1, doi: 10.1007/s43926-025-00096-7.
[5]G. Jin, Y. Liang, Y. Fang, Z. Shao, J. Huang, J. Zhang, and Y. Zheng, “Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey,” arXiv preprint, 2023, arXiv:2303.14483.
[6]A. Aboshosha, A. Haggag, N. George, et al., “IoT-based data-driven predictive maintenance relying on fuzzy system and artificial neural networks,” Scientific Reports, 2023, vol. 13, p. 12186, doi: 10.1038/s41598-023-38887-z.
[7]E. Zero, M. Sallak, and R. Sacile, “Predictive maintenance in IoT-monitored systems for fault prevention,” Journal of Sensor and Actuator Networks, 2024, vol. 13, no. 5, p. 57, doi: 10.3390/jsan13050057.
[8]S. Elkateb, A. Métwalli, A. Shendy, and A. E. B. Abu-Elanien, “Machine learning and IoT–based predictive maintenance approach for industrial applications,” Alexandria Engineering Journal, 2024, vol. 88, pp. 298–309, doi: 10.1016/j.aej.2023.12.065.
[9]T. Li, C. Sun, O. Fink, Y. Yang, X. Chen, and R. Yan, “Filter-informed spectral graph wavelet networks for multiscale feature extraction and intelligent fault diagnosis,” IEEE Transactions on Cybernetics, 2024, vol. 54, no. 1, pp. 506–518, doi: 10.1109/TCYB.2023.3256080.
[10]C. Atticus, V. Peyton, and M. Maximilia, “Graph neural networks for reliability prediction in smart city infrastructure systems,” Jurnal Teknik Informatika CIT Medicom, 2024, vol. 16, pp. 242–253.
[11]Y. Wang, J. Zhao, D. Tang, et al., “Intelligent fault prediction and diagnosis for wind-powered heating systems using graph neural networks,” Scientific Reports, 2025, vol. 15, p. 39068, doi: 10.1038/s41598-025-25884-7.
[12]K. F. Niresi, M. Zhao, H. Bissig, H. Baumann, and O. Fink, “Spatial-temporal graph attention fuser for calibration in IoT air pollution monitoring systems,” arXiv preprint, 2023, arXiv:2309.04508.
[13]V. Sharma, R. T. Oddon, P. Tesini, J. Ravesloot, C. Taal, and O. Fink, “Equi-Euler GraphNet: An equivariant, temporal-dynamics informed graph neural network for dual force and trajectory prediction in multi-body systems,” Mechanical Systems and Signal Processing, 2025, vol. 241, p. 113533, doi: 10.1016/j.ymssp.2025.113533.
[14]M. M. Topu, M. A. Anik, A. T. Wasi, and M. M. Ahsan, “Digital twin-driven pavement health monitoring and maintenance optimization using graph neural networks,” arXiv preprint, 2025, arXiv:2511.02957.
[15]X. Chen and K. Cheng, “Cutting tool remaining useful life prediction using multi-sensor data fusion through graph neural networks and transformers,” Machines, 2025, vol. 13, no. 11, p. 1027, doi: 10.3390/machines13111027.
[16]S. Qiu, “Optimizing predictive maintenance in intelligent manufacturing: An integrated FNO-DAE-GNN-PPO MDP framework,” arXiv preprint, 2025, arXiv:2511.05594.
[17]K. Varalakshmi and J. Kumar, “Optimized predictive maintenance for streaming data in industrial IoT networks using deep reinforcement learning and ensemble techniques,” Scientific Reports, 2025, vol. 15, p. 27201, doi: 10.1038/s41598-025-10268-8.
[18]S. Aslam, A. Navarro, A. Aristotelous, E. Garro Crevillen, A. Martínez-Romero, Á. Martínez-Ceballos, A. Cassera, K. Orphanides, H. Herodotou, and M. P. Michaelides, “Machine learning-based predictive maintenance at smart ports using IoT sensor data,” Sensors, 2025, vol. 25, no. 13, p. 3923, doi: 10.3390/s25133923.
[19]W. Li and T. Li, “Comparison of deep learning models for predictive maintenance in industrial manufacturing systems using sensor data,” Scientific Reports, 2025, vol. 15, p. 23545, doi: 10.1038/s41598-025-08515-z.
[20]P. Endla, S. Bhardwaj, P. Mathiyalagan, K. Akila, P. Sanjeevkumar, and M. Srinivasulu, “AI-Driven Predictive Maintenance Framework for Smart Manufacturing: Real-Time Deployment, Multi-Sensor Fusion and Scalable Efficiency Optimization,” in Proc. 1st International Conference on Research and Development in Information, Communication, and Computing Technologies, 2025, pp. 782–789. doi: 10.5220/0013943600004919.
[21]T. Lindgren, O. Steinert, O. Andersson Reyna, Z. Kharazian, and S. Magnússon, “SCANIA component X dataset: A real-world multivariate time series dataset for predictive maintenance (version 2),” Scania CV AB Dataset, 2024, doi: 10.5878/jvb5-d390.