This study focuses on evaluating the reliability of transport maintenance depots in South Africa, which are crucial for ensuring efficient transportation systems. A comprehensive data analysis approach was employed, incorporating historical data from multiple depots across South Africa. A Box-Jenkins ARIMA model was utilised to forecast future reliability trends with a confidence interval of ±5% for predictions. The analysis revealed consistent fluctuations in maintenance demand over seasons, with an average fluctuation rate of 20%. This pattern significantly influenced the accuracy of our time-series forecasting model. This study confirms the effectiveness of the ARIMA model in predicting depot reliability, offering a tool for strategic decision-making in maintenance operations. The findings suggest that further research should focus on incorporating additional variables such as economic conditions and technological advancements to enhance predictive accuracy. Maintenance Depot Systems, Reliability Analysis, Time-Series Forecasting, ARIMA Model The maintenance outcome was modelled as Y₈ₓ=₀+₁X₈ₓ+uᵢ+₈ₓ, with robustness checked using heteroskedasticity-consistent errors.
Nxumalo et al. (Sun,) studied this question.