Reliability Forecasting of a Load-Haul-Dump Machine: A Comparative Study of ARIMA and Neural Networks

Both the autoregressive integrated moving average (ARIMA or the Box–Jenkins technique) and artificial neural networks (ANNs) are viable alternatives to the traditional reliability analysis methods (e.g., Weibull analysis, Poisson processes, non‐homogeneous Poisson processes, and Markov methods). Time series analysis of the times between failures (TBFs) via ARIMA or ANNs does not have the limitations of the traditional methods such as requirements/assumptions of a priori postulation and/or statistically independent and identically distributed observations for TBFs. The reliability of an LHD unit was investigated by analysis of TBFs. Seasonal autoregressive integrated moving average (SARIMA) was employed for both modeling and forecasting the failures. The results were compared with a genetic algorithm‐based (ANNs) model. An optimal ARIMA model, after a Box–Cox transformation of the cumulative TBFs, outperformed ANNs in forecasting the LHD's TBFs.