Generalized T distribution and its applications to process data reconciliation and process monitoring

Abstract

Process data are conventionally characterized by normal distribution and techniques based on this assumption could suffer performance and efficiency losses when the assumption is violated. In this paper, the generalized T distribution is introduced and its robustness characteristics are investigated. Using this probability density function to characterize the process data, it is shown that both efficiency as well as robustness of some of the techniques currently employed in process systems engineering can be improved. Performance is illustrated by its applications to process data reconciliation and process fault detection of chemical engineering case studies.