Maximum-likelihood mixture factor analysis model and its application for process monitoring

In the present paper, a mixture form of the factor analysis model is developed under the maximum-likelihood framework. In this new model structure, different noise levels of process variables have been considered. Afterward, the developed mixture factor analysis model is utilized for process monitoring. To enhance the monitoring performance, a soft combination strategy is then proposed to integrate different local monitoring results into a single monitoring chart, which is based on the Bayesian inference method. To test the modeling and monitoring performance of the proposed mixture factor analysis method, a numerical example and the Tennessee Eastman (TE) benchmark case studies are provided.