Improved disturbance and fault signal modeling via Hidden Markov Models

Understanding and modeling disturbances play a critical part in designing effective advanced model-based control solutions. Existing linear, stationary disturbance models are oftentimes limiting in the face of time-varying characteristics typically witnessed in process industries. These include intermittent drifts, abrupt changes, temporary oscillations, and outliers. This work proposes a Hidden-Markov-Model-based framework to deal with such situations that exhibit discrete, modal behavior. The usefulness of the proposed disturbance framework is demonstrated through two examples: i) tracking abruptly changing feed conditions in the context of a second generation bioethanol fermentor and ii) tracking stiction, a well known problems known to occur in valves.