This paper presents a novel model predictive control configuration for nonlinear distributed parameter systems based on least squares support vector machine. First, a data‐based modeling methodology for an unknown nonlinear distributed parameter system is introduced. Subsequently, the model predictive control framework based on the aforementioned model is presented at the measured point. To verify the effectiveness and feasibility of the control arithmetic, simulation results from a tubular reactor with the controller designed by the presented procedure are given.

This manuscript addresses a new multivariate generalized predictive control strategy using the least squares support vector machine for parabolic distributed parameter systems. First, a set of proper orthogonal decomposition-based spatial basis functions constructed from a carefully selected set of data is used in a Galerkin projection for the building of an approximate low-dimensional lumped parameter systems. Then, the temporal autoregressive exogenous model obtained by the least squares support vector machine is applied in the design of a multivariate generalized predictive control strategy. Finally, the effectiveness of the proposed multivariate generalized predictive control strategy is verified through a numerical simulation study on a typical diffusion-reaction process in radical symmetry.

No abstract

No abstract