Neural Adaptive Singularity-Free Control by Backstepping for Uncertain Nonlinear Systems
An adaptive neural control approach based on backstepping is presented. Unmodelled dynamics or external disturbances are considered in the nonlinear models. Approximating nonlinear dynamic is one of the performances of multi-layer feedforward neural networks. By the Lyapunov’s stability theory, the NN weights are turned on-line with no prior training needed. An important feature of the presented approach is that by modifying a novel quasi-weighted Lyapunov function, the possible control singularity in the design of NN adaptive controller is avoided effectively. Finally, the approach is applied in CSTR system. The simulation result is given to demonstrate the feasibility and effectiveness of the proposed method.
Unable to display preview. Download preview PDF.