Time-Series Forecasting Model for Measuring System Reliability in Industrial Machinery Fleets of South Africa

Industrial machinery fleets in South Africa face challenges related to maintenance and reliability. Current methods for evaluating system performance are often inadequate. A time-series forecasting model was developed using an autoregressive integrated moving average (ARIMA) method. The model's accuracy and robustness were assessed through cross-validation techniques. The ARIMA model showed a high degree of accuracy, with predictions within ±5% of actual system failures over the testing period. The developed ARIMA model effectively forecasts system reliability in industrial machinery fleets, offering significant improvements compared to existing methods. Implementing this forecasting model can lead to more efficient maintenance schedules and reduced downtime for South African industrial operations. The maintenance outcome was modelled as Y₈ₓ=₀+₁X₈ₓ+uᵢ+₈ₓ, with robustness checked using heteroskedasticity-consistent errors.