Terminal Sliding Mode Control Based on Neural Network

The paper present a new learning algorithm for fuzzy neural network (FNN) systems to approximate unknown nonlinear continuous functions. The concept of exponential fast terminal sliding mode is introduced into the learning algorithm to improve approximation ability. The training algorithm guarantees that the approximation is stable and converges to the optimal approximation function with improved speed. The proposed FNN approximator is then applied in the control of an unstable nonlinear system. Simulation results demonstrate that the proposed method can obtain good approximation ability and tracing control of nonlinear dynamic system.