📞 +91-7667918914 | ✉️ iarjset@gmail.com
International Advanced Research Journal in Science, Engineering and Technology
International Advanced Research Journal in Science, Engineering and Technology A Monthly Peer-Reviewed Multidisciplinary Journal
ISSN Online 2393-8021ISSN Print 2394-1588Since 2014
IARJSET aligns to the suggestive parameters by the latest University Grants Commission (UGC) for peer-reviewed journals, committed to promoting research excellence, ethical publishing practices, and a global scholarly impact.
← Back to VOLUME 13, ISSUE 10, OCTOBER 2026

Development of a Condition-Based Maintenance Model for AC Traction Motors in Electric Locomotives: A Case Study of Tanzania Standard Gauge Railway

Daud Peter Edward, John Mahona

👁 9 views📥 3 downloads
Share: 𝕏 f in ✈ ✉
Abstract: AC traction motors are mission-critical components of electric locomotives operating on the Tanzania Standard Gauge Railway (SGR), yet their failures occur over a wide and inconsistent range of operating hours, making conventional time-based maintenance insufficient for condition-sensitive degradation. This study developed and evaluated a locally calibrated condition-based maintenance (CBM) model for AC traction motors in the Tanzania SGR environment. A mixed-methods design was applied using 20 recorded motor-failure events from August 2024 to October 2025, complemented by healthy-operation records and maintenance personnel inputs. Reliability analysis used Weibull estimation to characterize failure behaviour, Kaplan-Meier analysis to estimate survival probability, FMEA to prioritize failure modes, FTA to identify failure causes and Cox regression to assess factors affecting failure risk. These outputs were integrated to develop the condition-based maintenance model. The dominant failure categories were mechanical (35%), electrical (25%), thermal (25%) and environmental (15%). Bearings represented 25% of failures, followed by stator windings (20%), rotor (15%), cooling fans (15%), insulation (15%) and shafts (10%). The fitted Weibull model produced a shape parameter of β=1.87 and a scale parameter of η=2,612 operating hours, indicating a wear-out-dominant failure pattern, while the estimated mean time between failures was 2,319 hours. The Cox model achieved a concordance index of 0.82. Validation produced an ROC AUC of 0.85, sensitivity of 83% at an 18% false-positive rate and a Hosmer- Lemeshow goodness-of-fit p-value of 0.60. Operational thresholds were established for vibration, stator-winding temperature, insulation resistance and predicted failure probability. The model-guided strategy indicated potential reductions of 32% in unplanned downtime and 28% in spare-parts replacement costs. The findings support adoption of a locally calibrated CBM framework to improve traction-motor reliability, maintenance planning and SGR fleet availability.

Keywords: Condition-based maintenance, AC traction motor, reliability modelling, Weibull analysis, Kaplan-Meier, Cox proportional hazards, FMEA, FTA, Tanzania SGR.

How to Cite:

[1] Daud Peter Edward, John Mahona, “Development of a Condition-Based Maintenance Model for AC Traction Motors in Electric Locomotives: A Case Study of Tanzania Standard Gauge Railway,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.131041

Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.