AN OPTIMAL NONLINEAR REGULATOR DESIGN WITH NEURAL-NETWORK AND FIXED-POINT THEOREM

A new optimal nonlinear regulator design method is developed by applyi ng a multi-layered neural network and a fixed point theorem for a nonl inear controlled system. Based on the calculus of variations and the f ixed point theorem, an optimal control law containing a nonlinear mapp ing of the state can be derived. Because the neural network has not on ly a good learning ability but also an excellent nonlinear mapping abi lity, the neural network is used to represent the state nonlinear mapp ing after some learning operations and an optimal nonlinear regulator may be formed. Simulation demonstrates that the new nonlinear regulato r is quite efficient and has a good robust performance as well.