Explicit Approximate Nonlinear Predictive Control Based on Neural Network Models

Nonlinear Model Predictive Control (NMPC) algorithms are based on various nonlinear models. Among others, an on-line optimization approach for NMPC based on neural network models can be found in the literature. Nevertheless, NMPC with on-line optimization is time consuming. On the other hand, an explicit solution to the NMPC problem would allow efficient on-line computations as well as verifiability of the implementation. This paper suggests an approximate multi-parametric Nonlinear Programming approach to explicit solution of NMPC problems for constrained nonlinear systems based on neural network models. In particular, the reference tracking problem is considered. The approach builds an orthogonal search tree structure of the state space partition and consists in constructing a feasible PWL approximation to the optimal control sequence.