Development of a Predictive Maintenance Model to Enhance Reliability in Overhead Catenary Systems at Tanzania Railways Corporation: A Case of the Standard Gauge Railway (SGR) from Dar es Salaam to Morogoro

Jamali Hudu Katakweba; Respicius Kiiza

doi:10.37284/eaje.8.2.3780

Jamali Hudu Katakweba Dar es Salaam Institute of Technology
Respicius Kiiza Dar es Salaam Institute of Technology

DOI: https://doi.org/10.37284/eaje.8.2.3780

Keywords: Predictive Maintenance, Overhead Catenary Systems, Railway Reliability, Multiple Regression Analysis, Tanzania Railways Corporation

Share Article:

Abstract

in overhead catenary systems at Tanzania Railways Corporation's Standard Gauge Railway from Dar es Salaam to Morogoro. The research aimed to identify factors affecting OCS reliability, formulate a mathematical predictive model, and validate its performance. A mixed-methods approach involving surveys of 60 professionals, field observations, and multiple regression analysis was employed. Data collection spanned a period of twelve months (2024-2025), encompassing operational parameters, environmental conditions, maintenance records, and system performance metrics, which were analysed using SPSS software. Relative Importance Index analysis identified seven critical factors: wire wear (RII = 0.9100), voltage deviation (RII = 0.9067), low conductivity (RII = 0.8867), support strength (RII = 0.8833), wire tension (RII = 0.8733), excess span length (RII = 0.8733), and high temperature (RII = 0.8700). Five factors showed minimal influence with RII values below 0.31. The multiple regression model achieved R = 0.99 and R² = 0.98, with 98% of the variance in OCS reliability explained by selected factors. ANOVA confirmed statistical significance (F = 13.286, p < 0.05). The predictive equation: Reliability = 0.990 - 0.071X₁ - 0.043X₂ - 0.011X₃ + 0.006X₄ + 0.009X₅ - 0.003X₆ - 0.006X₇. Model validation showed 80.4% prediction accuracy compared to 82% actual reliability, demonstrating effectiveness under both optimal (99.6% vs. 100%) and degraded conditions (44.4% vs. 44%). The model provides a framework for transitioning from reactive to proactive maintenance strategies, enabling Tanzania Railways Corporation to optimise resource allocation and enhance system reliability.

Downloads

Download data is not yet available.

References

Chen, Q., Cao, J., & Zhu, S. (2023). Data-driven monitoring and predictive maintenance for engineering structures: Technologies, implementation challenges, and future directions. IEEE Internet of Things Journal, 10(16), 14527-14551.

Chen, X., Zhang, H., Liu, P., & Zhao, D. (2022). Research on Catenary condition maintenance strategy based on multi-objective optimization. International Conference on Internet of Things and Machine Learning (IoTML 2021),

Chen, Y., Song, B., Zeng, Y., Du, X., & Guizani, M. (2023). A deep learning-based approach for fault diagnosis of current-carrying rings in the catenary system. Neural Computing and Applications, 1-13.

Cheng, H., Cao, Y., Wang, J., Zhang, W., & Zeng, H. (2020). A preventive, opportunistic maintenance strategy for the catenary system of high-speed railways based on reliability. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 234(10), 1149-1155.

Finner, L., Poetsch, G., Sarnes, B., & Kolbe, M. (2015). Program for catenary–pantograph analysis, PrOSA statement of methods and validation according EN 50318. Vehicle System Dynamics, 53(3), 305-313.

Li, K., Feng, C., Jin, S., Yao, Y., & Zhou, N. (2021). Effect of Ambient Temperature on the Catenary System. IOP Conference Series: Earth and Environmental Science,

Lin, S., Shang, C., Li, N., Sun, X., Feng, D., & He, Z. (2022). An optimization method for maintenance resource allocation in electrified railway catenary systems. IEEE Transactions on Industry Applications, 59(1), 641-651.

Liu, J., Jiao, Z., Zhang, C., Ning, K., Shi, R., & Gu, H. (2023). Joint Scheme for Electric Locomotive Evacuation and Distribution System Restoration with Faults of External Power Supply Systems. IEEE Transactions on Transportation Electrification.

Liu, W., Liu, Z., Núñez, A., Wang, L., Liu, K., Lyu, Y., & Wang, H. (2018). Multi-objective performance evaluation of the detection of catenary support components using DCNNs. IFAC-PapersOnLine, 51(9), 98-105.

Mahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR).[Internet], 9(1), 381-386.

Theissler, A., Pérez-Velázquez, J., Kettelgerdes, M., & Elger, G. (2021). Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry. Reliability engineering & system safety, 215, 107864.

Ucar, A., Karakose, M., & Kırımça, N. (2024). Artificial intelligence for predictive maintenance applications: key components, trustworthiness, and future trends. Applied Sciences, 14(2), 898.

Uebel, H., Fitzke, A., & Warlitz, J. (2001). European Standards in the Field of Railway Signalling and their Influence on Software Testing Methods. Software Quality: State of the Art in Management, Testing, and Tools, 209-224.

Van Dinter, R., Tekinerdogan, B., & Catal, C. (2022). Predictive maintenance using digital twins: A systematic literature review. Information and Software Technology, 151, 107008.

Wang, H., Zhang, W., Yang, D., & Xiang, Y. (2022). Deep-learning-enabled predictive maintenance in the industrial internet of things: methods, applications, and challenges. IEEE Systems Journal, 17(2), 2602-2615.

Wu, G., Dong, K., Xu, Z., Xiao, S., Wei, W., Chen, H., Li, J., Huang, Z., Li, J., & Gao, G. (2022). Pantograph–catenary electrical contact system of high-speed railways: recent progress, challenges, and outlooks. Railway Engineering Science, 30(4), 437-467.

Xin, T., Roberts, C., Weston, P., & Stewart, E. (2020). Condition monitoring of railway pantographs to achieve fault detection and fault diagnosis. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 234(3), 289-300.

Zhan, D., Jing, D., Wu, M., Zhang, D., Yu, L., & Chen, T. (2018). An accurate and efficient vision measurement approach for railway catenary geometry parameters. IEEE Transactions on Instrumentation and Measurement, 67(12), 2841-2853.

Zhu, J., Zhang, H., Chen, M., Xu, Z., Qi, H., Yin, L., Wang, J., & Hu, Y. (2015). A procedural modelling method for virtual high-speed railway scenes based on model combination and spatial semantic constraint. International Journal of Geographical Information Science, 29(6), 1059-1080.