Reinforcement linearization control system

The objective of the article is to provide an effective linearization contr ol approach for a nonlinear system. Three reinforcement back propagation le arning algorithms (RBPs), based on different step-ahead predictions, are pr oposed to build the affine linear model of a nonlinear system by means of a composed neural network structure. The approach is used to cancel the effe ct of nonlinearity of a plant. Reinforcement back propagations can compensa te the nonlinearity of the system dynamics between the outputs of the refer ence model and the system responses. In other words, the role of the compos ed neural plant is to perform model matching for a linearized system. Based on the derivation of RBPs, a synthetic model, a reinforcement nonlinear co ntrol system (RNCS) is developed. This scheme excels the conventional appro aches and RBPs. The proposed Learning schemes are implemented to linearize a pendulum system. The simulation has been done to illustrate the performan ce of the proposed learning schemes.