Premium
Reliability Forecasting of a Load‐Haul‐Dump Machine: A Comparative Study of ARIMA and Neural Networks
Author(s) -
Dindarloo Saeid
Publication year - 2016
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.1844
Subject(s) - autoregressive integrated moving average , artificial neural network , reliability (semiconductor) , autoregressive model , statistics , weibull distribution , engineering , box–jenkins , time series , econometrics , reliability engineering , computer science , mathematics , artificial intelligence , power (physics) , physics , quantum mechanics
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. Copyright © 2015 John Wiley & Sons, Ltd.