Nonlinear adaptive inverse control based on least squares support vector machines

A nonlinear adaptive inverse control structure based on least squares support vector machines (LS-SVM) is proposed in this paper. It can solve the problems such as overlearning, local minimum, and the curse of dimensionality', which neural networks usually have. Least squares support vector algorithm is characterized and used for identifying the model and inverse model of a nonlinear plant, furthermore, is used to control the performance And to cancel the disturbance of the plant. The two processes are treated separately, and thus can be optimized respectively. Simulation results have proved its validity and effectiveness.