Dynamic modelling and control of industrial processes with particle filtering algorithms

Abstract We use a probabilistic approach to estimate the operating conditions and guide an automatic control system for industrial processes. The jump Markov linear Gaussian (JMLG) model is adopted to describe process behavior as a dynamic mixture of linear models. Based on the JMLG model, we use Particle Filtering (PF) algorithms to make real-time estimates of the operating conditions of the process. The PF estimate is used to adapt an automatic feedback control system. We tested our approach against three standard control strategies using a real nonlinear process. The results indicate that implementation of a PF state estimator can lead to better control strategies.