Using neural network and decision tree for machine reliability prediction

Overall equipment efficiency (OEE) is widely used in industry. OEE is the combination of availability efficiency (AE), operation efficiency (OE), rate efficiency (RE), and quality efficiency (QE). In general, OEE, AE, OE, RE, or QE are only calculated as part of a management consultancy exercise. In the present research, a group of washing machines from a TFT-LCD manufacturing company was used for the case study. Because AE is strongly related to the reliability of a machine, this research aims to use collected AE data for predicting the reliability of the machine. Four methods are proposed for predicting the machine's reliability. The results show that the combination of neural networks and decision trees based on the previous eight AE values has the best performance in predicting the reliability of TFT-LCD washing machines.