Nonlinear Control with Neural Networks
Layered neural networks adapted by means of the back propagation algorithm discovered by Rumelhart, Hinton, and Williams (1986), Parker (1985), and Werbos (1974) are powerful tools for pattern recognition, associative memory, and adaptive filtering. In this chapter, adaptive neural networks will be used to solve nonlinear adaptive control problems that are very difficult to solve with conventional methods. The methodology shows promise for application to control problems that are so complex that analytical design techniques do not exist
and may not exist for some time to come. Neural networks can be used to implement highly nonlinear controllers with weights or internal parameters that can be determined by a self-learning process.