<![CDATA[With the complexity increase in industrial production process, the traditional Proportion-Integration-Differentiation(PID) control can not meet the requirements of the control system performance. Because neural network has the ability of adaptive, self-learning and nonlinear function approximation, control equality of system is improved if it is combined with traditional PID. In the paper, Hopfield neural network based on Hebb rules is used to identify the parameters of system, and then the state space model is established. Hopfield Neural network has the function of optimal calculation, PID controller based on Hopfield neural network is designed for a system can optimize the parameter of PID in real-time and improve control accuracy. Simulation result show the performance index is greatly improved. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4925]]>
