Nonlinear Control System Intelligent Identification Using Optimized Support Vector Machines

Nonlinear control system identification is studied using neoteric optimized Least Squares Support Vector Machines (LS-SVM) in this paper. Firstly, a multi-layer adaptive optimizing parameters algorithm is developed for improving learning and generalization ability of least squares support vector machines. According to different learning problems, the optimization approach can obtain appropriate LS-SVM parameters adaptively. Then, a nonlinear control system is identified by improved LS-SVM. The results show that the optimization approach can acquire best-optimized parameters for LS-SVM, and optimized LS-SVM can provide excellent control system identification precision and excellent convergence. And also, the multi-layer adaptive optimizing parameters algorithm may be appropriately extended to other types of support vector machines.