X¯ Control Chart Pattern Identification Through Efficient Off-Line Neural Network Training

Back-propagation pattern recognizers (BPPR) are proposed to identify unnatural patterns exhibited on Shewhart control charts. These unnatural patterns, such as cycles and trends, can provide valuable information for real-time process control. In a computer-integrated manufacturing environment, the operator need not routinely monitor the control chart but, rather, can be alerted to patterns by a computer signal generated by the proposed algorithm. In this paper, an off-line analysis is performed to investigate the training and learning speed of these BPPRs on simulated X¯ data. The best configuration of the network is further tested to demonstrate the classification capability of the proposed BPPR.