Generalized Input-Output Hidden-Markov-Models for Supervising Industrial Processes

Abstract

Often in industrial processes, batches of material are processed sequentially and repeatedly through a deterministic sequence of process steps. The possibly large number of sensor measurements collected throughout such industrial processes require supervisory modeling techniques that allow for characterizing the operating conditions (or states) of these process steps. This would allow for inference and predictions over the operating conditions of the current and upcoming process steps (e.g., abnormal behavior, failures, etc.) which may significantly assist the operators of the process. Traditionally, such inference questions in repeated processes can be handled in a rather straightforward manner via Input-Output Hidden Markov Models (IOHMM). However, standard IOHMM are limited to repeated and identical processes, while industrial processes may comprise multiple non-identical process steps and possibly with non-standard interdependencies between process steps. For this reason, in this paper we propose a generalization of standard IOHMM that is more appropriate for modeling industrial processes. Furthermore, we derive the update recursions for training such models and we show analytically that such update recursions guarantee an increase in the likelihood of the observation sequences.