HYBRID EDGE AI AND GRAPH NEURAL NETWORK FRAMEWORK FOR INTELLIGENT RAILWAY CONDITION MONITORING

This research presented a Hybrid Edge AI and Graph Neural Network Framework for intelligent railway condition monitoring. The proposed architecture integrates IoT sensing, edge computing, and graph-based deep learning to provide accurate, scalable, and real-time monitoring of railway infrastructure. Experimental results demonstrated superior predictive performance compared to conventional machine learning and deep learning approaches. The framework offers a practical solution for next-generation railway asset management systems by enabling early fault detection, reducing maintenance costs, and improving operational safety. Future research will focus on integrating digital twin technology, federated learning, explainable AI mechanisms, and large-scale deployment across national railway networks.

1.                Kipf, T.N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ICLR. 2.                Velickovic, P., et al. (2018). Graph Attention Networks. ICLR. 3.                Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive Representation Learning on Large Graphs. NeurIPS. 4.                Liu, R., et al. (2022). Artificial Intelligence for Predictive Maintenance in Railway Systems. Reliability Engineering & System Safety, 220, 108289. 5.                Qi, J., et al. (2023). Edge Intelligence for Industrial Predictive Maintenance: A Survey. IEEE Internet of Things Journal, 10(7), 5841–5860. 6.                Carvalho, T.P., et al. (2019). Machine Learning Methods Applied to Predictive Maintenance. Computers & Industrial Engineering, 137, 106024. 7.                McMahan, B., et al. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. AISTATS. 8.                Wu, Z., et al. (2021). A Comprehensive Survey on Graph Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24.