A big data-driven predictive control approach for nonlinear processes using behaviour clusters

Abstract

A novel big data-driven predictive control (BDPC) approach for nonlinear processes is proposed. To deal with nonlinear process behaviours, the process behaviour space, represented by a set of input–output variable trajectories, is partitioned into linear sub-behaviour spaces (clusters), based on linear inclusion of nonlinear behaviours. A behaviour space (represented using Hankel matrices) partitioning approach is developed based on subspace angles. During online control, the BDPC controller locates the most relevant linear sub-behaviour based on the current online trajectory, which is then used to determine predictive control actions using receding horizon optimisation. The incremental stability and dissipativity conditions are developed to attenuate the effect of the error of approximating linear sub-behaviours on the output and guarantee closed-loop stability. These conditions are implemented as additional constraints during online data-driven predictive control. An example of controlling the Hall–Héroult process is used to illustrate the proposed approach.