A Novel Single-Encounter-Emphasise-Attention Neural Network for Predictive Maintenance in Urban Infrastructure

Tawfeeq Shawly , Ahmed A. Alsheikhy

CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (5) : 1444 -1462.

PDF (3122KB)
CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (5) :1444 -1462. DOI: 10.1049/cit2.70171
ORIGINAL RESEARCH
research-article
A Novel Single-Encounter-Emphasise-Attention Neural Network for Predictive Maintenance in Urban Infrastructure
Author information +
History +
PDF (3122KB)

Abstract

The Riyadh Metro represents a significant project in Saudi Arabia, designed to transform urban transportation and reduce traffic congestion within the city. With six metro lines and 85 stations, the network is expected to serve millions of passengers daily, necessitating innovative digitally driven maintenance approaches to ensure reliable efficient operation. We hypothesise that integrating Internet of things (IoT) sensors, digital twin technology, and a temporal graph neural network (TempGNN) enables real-time health monitoring. This paper introduces a real-time digital health monitoring framework that incorporates IoT sensors, digital twin technology, a proposed TempGNN and a new module single encounter-emphasise attention neural network (SEEA- NN). TempGNN exploits both temporal patterns and spatial relationships in these sensor data to feed SEEA-NN with its required data. SEEA-NN is designed to detect and assess the importance of rare single-occurrence failure precursors, often overlooked by conventional models, alongside recurring patterns. The proposed framework contains an input gating module to filter out noisy sensor data, a multihead encounter attention module that employs a specific attention head to isolate and enhance the signal from anomalous single-encounter events, and a temporal synthesis layer that combines these emphasised features with sequential data for thorough analysis. This enables the framework to predict potential failures with high accuracy of approximately 98%, allowing for proactive maintenance scheduling and decreased unplanned downtime by more than 30% and maintenance expenses by around 25%, whilst also enhancing energy efficiency and passenger satisfaction in simulations. This approach demonstrates a scalable model for the digital transformation of large-scale transport infrastructure and for implementing intelligent predictive maintenance in metro systems worldwide and in logistics fleets, container handling systems and freight rail networks.

Keywords

digital twin / logistics / predictive maintenance / real-time monitoring / Riyadh Metro / smart transportation / Vision 2030

Cite this article

Download citation ▾
Tawfeeq Shawly, Ahmed A. Alsheikhy. A Novel Single-Encounter-Emphasise-Attention Neural Network for Predictive Maintenance in Urban Infrastructure. CAAI Transactions on Intelligence Technology, 2026, 11 (5) : 1444-1462 DOI:10.1049/cit2.70171

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

E. Mirza, “ How the New Riyadh Metro Project Is Taking Saudi Arabia Closer to Vision 2030 Goals: Borderless Access Study Uncovers Key Insights,” accessed on, 1 2, 2025, https://borderlessaccess.com/blog/riyadh-metro-saudi-vision-2030-insights/.

[2]

Kingdom of Saudi Arabia, “ Saudi Vision 2030,” accessed on 12/11/2024, https://www.vision2030.gov.sa/media/rc0b5oy1/saudi_visio n203.pdf.

[3]

M. Shah, “ Riyadh Metro: Know all About Saudi Arabia's Largest 176-km Driverless Mass Rapid Transit System,” accessed on 15/2/2025, https://metrorailtoday.com/news/riyadh-metro-know-all-about-saudi-arabias-largest-176-km-driverless-mass-rapid-transit-system.

[4]

Royal Commission for Riyadh City, “ King Abdulaziz Project for Riyadh Public Transport,” accessed on, 12 14, 2024, https://www.rcrc.gov.sa/en/projects/king-abdulaziz-project-for-riyadh-public-transport/.

[5]

D. Wu, A. Zheng, W. Yu, et al., “ Digital Twin Technology in Transportation Infrastructure: A Comprehensive Survey of Current Applications, Challenges, and Future Directions,” Applied Sciences 15, no. 4 (2025): 1-44, https://doi.org/10.3390/app15041911.

[6]

Co-EDP, “ Digital Twins Reshape Urban Transportation: A game-changer for Smart Cities,” accessed on, 2 19, 2025, https://www.devdi scourse.com/article/technology/3262781-digital-twins-reshape-urban-transportation-a-game-changer-for-smart-cities.

[7]

D. Dimitrov, “ Forbes Technology Council, the Future of Transportation: AI, Connectivity and Safety in 2025,” accessed on, 2 19, 2025, https://www.forbes.com/councils/forbestechcouncil/2025/02/10/the-future-of-transportation-ai-connectivity-and-safety-in-2025/.

[8]

X. Di, Y. Fu, M. K. Turkcan, et al., “ AI-Powered Urban Transportation Digital Twin: Methods and Applications,” arXiv:2501.10396 (2025): 1-28.

[9]

V. Bouckova, “ Smart City Transportation Trends: Urban Digital Twins,” accessed on, 1 13, 2025, https://blog.goodvisionlive.com/smart-city-transportation-trends-urban-digital-twins.

[10]

Y. Gao, S. Qian, Z. Li, P. Wang, F. Wang, and Q. He, “ Digital Twin and Its Application in Transportation Infrastructure,” in 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI) (2021), 298-301.

[11]

X. Chang, R. Zhang, J. Mao, and Y. Fu, “ Digital Twins in Transportation Infrastructure: An Investigation of the Key Enabling Technologies, Applications, and Challenges,” IEEE Transactions on Intelligent Transportation Systems 25, no. 7 (2024): 6449-6471, https://doi.org/10.1109/tits.2024.3401716.

[12]

T. Li, Z. Bian, H. Li, et al., “ Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics for Urban Transportation Management,” arXiv:2407:15025 (2024): 1-37.

[13]

F. Ur Rahman, T. Ahmed, M. Hasan, and N. Jahan, “ Real-Time Obstacle Detection Over Railway Track Using Deep Neural Networks,” Procedia Computer Science 215 (2022): 289-298, https://doi.org/10.1016/j.procs.2022.12.031.

[14]

M. Hafsi, N. Hamour, and S. Ouchani, “ Predictive Maintenance for Smart Industrial Systems: A Roadmap,” in The 6th International Conference on Emerging Data and Industry (EDI40) (2023), 1-7.

[15]

V. Chauhan, M. Patel, S. Tanwar, S. Tyagi, and N. Kumar, “ IoT Enabled Real-Time Urban Transport Management System,” Computers and Electrical Engineering 86, no. 106746 (2020): 106746, https://doi.org/10.1016/j.compeleceng.2020.106746.

[16]

N. Bešinović, L. D. Donato, F. Flammini, et al., “ Artificial Intelligence in Railway Transport: Taxonomy, Regulations, and Applications,” IEEE Transactions on Intelligent Transportation Systems 23, no. 9 (2022): 14011-14024, https://doi.org/10.1109/tits.2021.3131637.

[17]

V. J. Hodge, S. O'Keefe, M. Weeks, and A. Moulds, “ Wireless Sensor Networks for Condition Monitoring in the Railway Industry: A Survey,” IEEE Transactions on Intelligent Transportation Systems 16, no. 3 (2015): 1088-1106, https://doi.org/10.1109/tits.2014.2366512.

[18]

I. Atanasov, E. Pencheva, V. Trifonov, and K. Kassev, “ Railway Cloud: Management and Orchestration Functionality Designed as Microservices,” Applied Sciences 14, no. 6 (2024): 1-22, https://doi.org/10.3390/app14062368.

[19]

University of California Irvine, “ MetroPT-3 Dataset,” accessed on, 1 19, 2025, https://archive.ics.uci.edu/dataset/791/metropt+3+dataset.

[20]

N. Davari, B. Veloso, R. P. Ribeiro, P. M. Pereira, and J. Gama, “ Predictive Maintenance Based on Anomaly Detection Using Deep Learning for Air Production Unit in the Railway Industry,” in 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA) (2021), 1-10, https://doi.org/10.1109/DSAA53316.2021.9564181.

[21]

L. Zhang, J. Kuang, Y. Teng, S. Xiang, L. Li, and Y. Zhou, “ LEAD-Net: Semantic-Enhanced Anomaly Feature Learning for Substation Equipment Defect Detection,” Processes 13, no. 2341 (2025): 2341, https://doi.org/10.3390/pr13082341.

[22]

Swathi, A. Gangula, M. R. Vootukuri, and R. Manchiryala, “ Real-Time Anomaly Detection and Predictive Maintenance in Metro Train APU Compressors: A Data-Driven Approach,” Social Science Journal 14, no. 5 (2024): 85-94.

[23]

H. T. M. Tran and D. Hogg, “ Anomaly Detection Using Prediction Error With Spatio-Temporal Convolutional LSTM,” arXiv:2205.08812v1 (2022).

[24]

F. Koçyiğit, F. Ünal, and S. Koçyiğit, “ Experimental Analysis and Modeling of the Thermal Conductivities for a Novel Building Material Providing Environmental Transformation,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects 42, no. 24 (2020): 3063-3079, https://doi.org/10.1080/15567036.2020.1811811.

[25]

A. E. Akan, F. Ünal, and F. Koçyiğit, “ Investigation of Energy Saving Potential in Buildings Using Novel Developed Lightweight Concrete,” International Journal of Thermophysics 42, no. 4 (2021): 4, https://doi.org/10.1007/s10765-020-02761-1.

[26]

A. A. Movassagh, J. A. Alzubi, M. Gheisari, et al., “ Artificial Neural Networks Training Algorithm Integrating Invasive Weed Optimization With Differential Evolutionary Model,” Journal of Ambient Intelligence and Humanized Computing 14, no. 5 (2023): 6017-6025, https://doi.org/10.1007/s12652-020-02623-6.

PDF (3122KB)

0

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉