Detection of process model change in PLS based performance monitoring

Abstract

The detection of process changes using a partial least squares (PLS) based monitoring scheme can be achieved through the interrogation of two metrics, Hotelling's T and the Q-statistic. The Q-statistic has been shown to be insensitive to small changes in the process model parameters. In this paper, a modified statistic based on the local approach is proposed to detect changes in the model parameters in a PLS based monitoring scheme. The performance of the Q-statistic is compared with the modified statistic through their application to fault detection in a continuous stirred tank reactor.