Quality control in hard disc drive manufacturing using pattern recognition technique

Computerized monitoring-diagnosis is an efficient technique to identify the source of unnatural variation (UV) in manufacturing process. In this study, a pattern recognition scheme (PRS) for monitoring-diagnosis the UVs was developed based on control chart pattern recognition technique. This PRS integrates the multivariate exponentially weighted moving average (MEWMA) control chart and artificial neural network (ANN) recognizer to perform two-stage monitoring-diagnosis. The first stage monitoring was performed using the MEWMA statistics, whereas the second stage monitoring-diagnosis was performed using an ANN. The PRS was designed based on bivariate process mean shifts between 0.75 sigma and 3.00 sigma, with cross correlation between rho = 0.1 and 0.9. The performance of the proposed PRS has been validated in quality control of hard disk drive component manufacturing. The validation proved that it is efficient in rapidly detecting UV and accurately classify the source of UV patterns. In a nutshell, the PRS will aid in realizing automated decision making system in manufacturing industry.