Intra-Batch Evolution Based Process Monitoring for Multiphase Batch Processes

Batch-wise variations, called intra-batch evolution here, widely exist in batch processes. In this paper, intra-batch evolution is tracked and monitored for multiphase batch processes. First, a batch cycle is divided into multiple phases. Within each phase, sliding windows are constructed for analysis of intra-batch relative variations, based on which different process modes are separated in order along batch direction. Meanwhile, the part of variations with significant increases in new modes is separated from the other. Consequently, the original two monitoring subspaces are further divided into four subspaces, specifically, two parts which make contribution and no contribution to alarming T 2 monitoring statistic, the part responsible for the out-of-control SPE monitoring statistic and the left final residuals. The application to a typical multiphase batch process with intra-batch evolution, injection molding start-up process, illustrates the feasibility and performance of the proposed algorithm.