Time-Series Forecasting Model for Evaluating System Reliability in Senegalese Industrial Machinery Fleets

Industrial machinery fleets in Senegal require robust reliability assessment methods to optimise maintenance schedules and prevent downtime. A time-series forecasting model was applied to historical data from industrial machinery fleets. The model's performance was evaluated for its accuracy and robustness, considering potential uncertainties in future maintenance needs. The time-series forecasting model demonstrated an accuracy rate of 85% in predicting system failures over a two-year period, with confidence intervals indicating a margin of error within ±10%. This study validates the effectiveness of the proposed time-series forecasting model for evaluating system reliability in Senegalese industrial machinery fleets. Industrial operators should implement this model to enhance fleet management and reduce maintenance costs. Time-Series Forecasting, System Reliability, Industrial Machinery Fleets, Senegal The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.