A generalized probabilistic monitoring model with both random and sequential data

Many multivariate statistical analysis methods and their corresponding probabilistic counterparts have been adopted to develop process monitoring models in recent decades. However, the insightful connections between them rarely studied. In this study, a generalized model (GPMM) is developed with both random sequential data. Since GPMM can be reduced various linear under specific restrictions, it analyze different methods. Using expectation maximization (EM) algorithm, parameters of are estimated for cases. Based on obtained parameters, statistics designed aspects system. Besides, distributions these rigorously derived proved, so that control limits calculated accordingly. After that, contribution presented identifying faulty variables once anomalies detected. Finally, equivalence based classical graphic further investigated. The conclusions study verified using numerical example Tennessee Eastman (TE) process. Experimental results illustrate proposed subject distributions, they equivalent deterministic restrictions.