Incorporating fuzzy c-means and a back-propagation network ensemble to job completion time prediction in a semiconductor fabrication factory

Job completion time prediction is a critical task to a semiconductor fabrication factory. To further enhance the effectiveness/accuracy of job completion time prediction in a semiconductor fabrication factory, a hybrid fuzzy c-means (FCM) and back propagation network (BPN) approach is proposed in this study. In the proposed FCM–BPN approach, input examples are firstly pre-classified with FCM before they are fed into the BPN. Then, examples belonging to different categories are learned with different BPNs but with the same topology. After learning, these BPNs form a BPN ensemble that can be applied to predict the completion time of a new job. The output of the BPN ensemble is derived by aggregating the outputs from the component BPNs with another BPN and determines the completion time forecast. To validate the effectiveness of the proposed methodology and to make comparison with some existing approaches, the actual data in a semiconductor fabrication factory were collected. According to experimental results, the prediction accuracy of the proposed methodology was significantly better than those of some existing approaches. Besides, applying the fuzzy set theory was shown to be very effective in forming job categories and in deriving a representative value from the BPN ensemble. Both contributed to the superiority of the proposed methodology.