Adaptive Inverse Control of Nonlinear Systems using PID Dynamic Neural Networks

A new adaptive inverse control (AIC) system based on PID dynamic neural networks is presented in this paper. The system consists of two PID dynamic neural networks: one is applied to identifying the plant; the other approximates inverse model of the plant. A BPTM online learning algorithm for this system was described in detail. Simulation results show PID dynamic neural networks-based identifier and controller work well and the given BPTM online learning algorithm is efficient in the application of adaptive inverse control (AIC).