作者: W. Gao , R.R. Selmic
关键词:
摘要: A neural net (NN)-based actuator saturation compensation scheme for the nonlinear systems in Brunovsky canonical form is presented. The that leads to stability, command following, and disturbance rejection rigorously proved verified using a general "pendulum type" robot manipulator dynamical systems. Online weights tuning law, overall closed-loop system performance, boundedness of NN are derived guaranteed based on Lyapunov approach. assumed be unknown compensator inserted into feedforward path. Simulation results indicate proposed can effectively compensate nonlinearity presence uncertainty.