Model Reference Adaptive Control Based on BP Neural Networks

A scheme of model reference adaptive control based on BP neural network is presented in this paper. Two BP neural networks are used to identify and control unknown plants. Since a BP neural network has the properties of forward propagation of message and backward propagation of errors, the parameters of a network can be modified to get proper values. The BP identifier is also used as a channel for error propagation. Simulation results show the effectiveness of the proposed scheme.