ITERATIVE INVERSION OF NEURAL NETWORKS AND ITS APPLICATION TO ADAPTIVE-CONTROL

The results presented in this paper use an iterative constrained inversion technique to find the control inputs to the plant. That is, rather than training a controller network and placing this network directly in the feedback or feedforward paths, the forward model of the plant is learned, and iterative inversion is performed on line to generate control commands. The proposed control approach allows the controllers to respond on line to changes in the plant dynamics. This approach also attempts to avoid the difficulty of analysis introduced by most current neural network controllers, which place the highly nonlinear neural network directly in the feedback control path, by removing the network from the direct feedback path. Based on stability results of systems control and formal mechanisms of Lyapunov stability, a neural-network-based model reference adaptive controller (NN-MRAC) is also proposed for systems having significant dynamics between the control inputs and the observed (or desired) outputs and is demonstrated on a simple linear control system. These results are interpreted in terms of the need for a dither signal for on-line identification of dynamic systems.