Xz. Wang et Rf. Li, Combining conceptual clustering and principal component analysis for statespace based process monitoring, IND ENG RES, 38(11), 1999, pp. 4345-4358
Multivariate statistics and unsupervised machine learning have recently bee
n studied by many researchers for process monitoring and fault diagnosis. T
hese approaches often depend on calculating a similarity or distance measur
e to group data sets into clusters. Apart from giving predictions, they are
not able to give causal explanations on why a specific set of data is assi
gned to a particular cluster. In this work, a conceptual clustering approac
h is presented for designing state space based monitoring systems, which is
able to generate conceptual knowledge on the major variables which are res
ponsible for clustering, as well as projecting the operation to a specific
operational state. A critical issue in this approach is how to conceptually
represent dynamic trend signals. For this purpose, principal component ana
lysis is used for concept extraction from real-time dynamic trend signals.
The method is introduced using a continuous stirred tank reactor as a case
study. Application of the approach to a refinery methyl tert-butyl ether pr
ocess is also presented.