The Research On Methods Of Intelligent Control For Robot Tracking

Intelligent control theory is theory methods with some imitate people project control and information processing. Robotics is the newest scientific findings, has concentrated many kinds of disciplines, such as mechanical engineering, electronic engineering, computer project and artificial intelligence, etc., it is one of the most active fields of the development in science and technology at present. In this paper, the development of intelligent control technology and its application to robotic control are reviewed.In this paper, firstly, the basic principle of fuzzy control is introduced and analyzed in detail, and a fuzzy control method is proposed. It does not depend on the accurate mathematics model, can overcome the effects of the nonlinear, coupling and uncertain factors. Secondly, a radial basis function neural network based on orthogonal least squares (OLS) learning algorithm is presented, and is applied to identify the robot system. Then the abilities of fuzzy inductive inference and self-learning are realized by constructing fuzzy neural network (FNN) that combines fuzzy control and neural network together. FNN uses neural network to realize fuzzy inference. This make it has ability of fuzzy inductive inference and ability of tuning the way of inference. Since the construction of FNN has clear meaning, the design and initialization of FNN are also very easy, and a fuzzy Gaussian basis neural network is given in this paper. Thirdly, after analyzing the advantage and disadvantage of various kinds of learning algorithm of the FNN, a hybrid learning algorithm is introduced. First the genetic algorithm is used to optimize the FNN's parameters off-line. Then the BP algorithm is used to adjust the parameters on-line. Finally, for counteracting the defects of sliding-mode control, a neural network sliding-mode control system is designed in this paper. The Neural network is used to compensate the uncertainty of the system. Based on Lyapunov theorem, the structure of sliding-mode controller and the learning algorithm of the neural network are designed. So the stability of the system is guaranteed, and the dynamic performance of the system is improved.All proposed methods are applied on the robotic trajectory tracking control to counteract the effects of the nonlinear, coupling and uncertain factors in the robotic system in this paper. The results of the simulation experiments show that all proposed methods have good control performances. When they are applied to control robotic...