ADAPTIVE BATCH MONITORING USING HIERARCHICAL PCA

A new approach to monitoring batch processes using the process variabl e trajectories is presented. It was developed to overcome the need in the approach of Nomikos and MacGregor [P. Nomikos, J.F. MacGregor, Mon itoring of batch processes using multi-way principal components analys is, Am. Inst. Chem. Eng. J. 40 (1994) 1361-1375; P. Nomikos, J.F. MacG regor, Multivariate SPC charts for batch processes, Technometrics 37 ( 1995) 41-59; P. Nomikos, J.F. MacCregor, Multi-way partial least squar es in monitoring batch processes, Chemometrics Intell, Lab. Syst. 30 ( 1995) 97-108] for estimating or filling in the unknown part of the pro cess variable trajectory deviations from the current time until the en d of the batch. The approach is based on a recursive multi-block (hier archical) PCA/PLS method which processes the data in a sequential and adaptive manner. The rate of adaptation is easily controlled with a pa rameter which controls the weighting of past data in an exponential ma nner. The algorithm is evaluated on industrial batch polymerization pr ocess data and is compared to the multi-way PCA/PLS approaches of Nomi kos and MacGregor. The approach may have significant benefits when mon itoring multi-stage batch processes where the latent variable structur e can change at several points during the batch. (C) 1998 Elsevier Sci ence B.V. All rights reserved.