Study of system control simulation based on generalized congruence neural network

On real-time demand of neural network control system, the self-tuning PID control system´s structure and algorithm based on generalized congruence neural network(GCNN) are presented, in which the improved generalized congruence neural network is adopted for identifier, and the generalized congruence neuron is used as controller. The simulation results of nonlinear dynamical control system show that the proposed GCNN control system responses quickly and is stable, i.e., the proposed control system based on GCNN is feasible. Moreover, piecewise linear activation function in GCNN will in favor of its control system´s hardware realization and expanding application.