The reliability of process-control systems in industrial settings is critical for operational efficiency and safety. In many developing economies, systematic methodologies for forecasting and evaluating this reliability are lacking, leading to unplanned downtime and economic losses. This study aimed to develop and validate a time-series forecasting model for measuring and predicting the reliability of process-control systems. The objective was to provide a methodological framework for proactive maintenance planning. A longitudinal dataset of system failure events and maintenance logs was analysed. An autoregressive integrated moving average (ARIMA) model, specified as yₜ = c + ₁ yₓ-₁ + ₁ ₓ-₁ + ₜ, was developed and validated using a rolling-origin forecast evaluation. Model diagnostics included analysis of residual autocorrelation and Ljung-Box tests. The ARIMA (1, 1, 1) model provided the best fit, forecasting a 17. 5% improvement in mean time between failures over the forecast horizon. The 95% confidence interval for this improvement ranged from 12. 2% to 22. 8%, indicating a statistically significant positive trend in system reliability. The developed time-series model is a robust tool for forecasting process-control system reliability, enabling evidence-based maintenance strategies. Industry practitioners should adopt similar forecasting methodologies for capital planning. Further research should integrate real-time sensor data into the modelling framework. system reliability, time-series analysis, forecasting, process control, maintenance engineering, ARIMA modelling This paper presents a novel application of ARIMA modelling for forecasting industrial control-system reliability in a developing economy context, providing a validated methodological framework previously absent in the region.
Kigozi et al. (Fri,) studied this question.