Reliability forecasting assists the manager to efficiently track the operational performance and the system's reliability for follow-up actions. This study combines time series and neural network approaches to predict the system's reliability. Prediction of the time series based on the previous parameter value is used as the neural network's input. The proposed method can enhance the reliability forecasting ability and accelerate the convergence of network training. Moreover, two case studies are presented to demonstrate the effectiveness of the proposed procedure.
|Number of pages||12|
|Journal||Kung Yeh Kung Chieng Hsueh K'an/Journal of the Chinese Institute of Industrial Engineers|
|State||Published - 1 Jan 1997|