Study And Application Of Intelligent Sliding Mode Control

On the basis of summarizing of the research of intelligent sliding mode variable structure control,several sliding mode control schemes are proposed for a class of nonlinear system. And the fuzzy control, neural network and the quantum genetic algorithm are respectively incorporated into each scheme.Firstly, in order to solve the problems of how to acquire the fuzzy rules in the fuzzy sliding mode controller, the quantum genetic algorithm is used to optimize the fuzzy control rules and improve the performance of the controller.Next, a new fuzzy total-sliding-mode controller is designed, in which the fuzzy control and the sliding-mode control are incorporated. Using the total sliding mode surface as the input of the controller, the adaptive algorithm of the distance of the fuzzy singleton is figured out on the basis of the stability analysis of the Lyapunov function. The controller solves efficiently the unknown upper of parameter variance and external disturbance. Moreover, a scheme of composite sliding control is proposed, which is based on fuzzy neural network (FNN) and single neuron (SN). The SN is uniquely determined by the design of the global integral sliding mode surface, the output of which replaces the corrective control, and FNN is applied to mimic the equivalent control. As a result, the scheme reduces the chattering of the system and improves the robustness. The scheme is applied to the experiment of an inverted pendulum system to verify the validity and the performance.The simulation and the experiment results demonstrate the effectiveness of the above methods.