Application of Just-In-Time Statistical Process Control to Vinyl Acetate Monomer Process

摘要

A new fault detection method is proposed to solve the problems that obstruct industrial applications of multivariate statistical process control (MSPC) techniques. The proposed method is called Just-In-Time Statistical Process Control (JIT-SPC). JIT-SPC focuses on the distance from the current operation data to the normal operation data stored in the database because fault detection is based on whether normal data exist near the current operation data. In addition, JIT-SPC does not use complicated modeling methods or impractical assumptions that the conventional methods have. Therefore, JIT-SPC is designed easily and suitable for the practical use. In order to improve the performance of JIT-SPC, a technique for adapting its control limit to operating condition is proposed. The usefulness of JIT-SPC is demonstrated through a case study of the vinyl acetate monomer process. The results show that JIT-SPC with adaptive control limit can be applied to processes whose operating condition is changed and it can detect faults earlier than the conventional MSPC.