Abstract
A new process control and monitoring system for quality imprgvement, referred to as hierarchical quality improvement system (HiQIS), is proposed. HiQIS consists of data-driven quality improvement (DDQI), Run-to-Run (R2R) control, local control, and multivariate statistical process control (MSPC). The main features of HiQIS are: 1) to build a statistical quality model, 2) to analyze the cause of quality variation, 3) to select a few variables to be manipulated, 4) to optimize the operating condition, and 5) to realize the desired quality even if there is modeling error and disturbances. A typical problem encountered in real applications is product quality variation, which occurs even if operators attempt to keep operating conditions at constant. In addition, from the practical viewpoint, it is difficult to change many operating condition variables simultaneously. Therefore, in the present work, quality variation analysis and manipulated variables selection are mainly focused on. The usefulness of HiQIS and the proposed methods are demonstrated through a case study.
