Quality-relevant iterative relative analysis based sub-phase modeling for multiphase batch process monitoring

In the present work, quality-relevant relative analysis is iteratively conducted for time-slices within the same phase to capture the relative changes of process variation along time direction based on their influences on qualities. Thus, for each time slice within the same phase, two systematic subspaces are separated, revealing time-independent quality-relevant variation and time-dependent quality-relevant variation respectively. Only the time-independent variation which stays quality-related and similar with the same phase can be described by a unified phase model. The time-dependent variation reflects time-varying quality-related characteristics within each phase which has to be described by different models. For online monitoring, different types of quality-relevant variations can be supervised respectively in which the changes of process variation can be well tracked, providing reliable fault detection performance as well as enhanced process understanding. It is illustrated with a typical multiphase batch process.