Adaptive Fuzzy C-Means clustering in process monitoring

Quite often, quality control models fail because, e.g., the mean values are changing continuously. These kinds of changes, e.g., process drifts due to seasonal fluctuations, are common in an activated sludge waste-water treat ment plant in Finland. Different Fuzzy C-Means (FCM) clustering algorithms were tested in order to cope with these kinds of seasonal effects. Firstly, a Principal Component Analysis (PCA) model was constructed in order to vis ualize the data set and reduce the dimensionality of the problem. Then, sco re values of the PCA were used in the FCM. The cluster centers represented the different process conditions (winter and summer seasons). Different alg orithms were used to update the cluster centers or to give them some flexib ility. The testing of different FCM algorithms was carried out by using a s eparate test set. The adaptive and the flexible FCM algorithms were compare d to the basic non-adaptive FCM. For both cases, modifications are proposed and a simple strategy for updating the cluster centers is given. (C) 1999 Elsevier Science B.V. All rights reserved.