Temperature Control of Internal Mixer Based on RBF Neural Network

This paper considers the problem of poor control effect of the PID control algorithm in internal mixer temperature control process. Based on the strong robustness of the fuzzy control and the self-learning characteristics of the neural network, a fuzzy RBF neural network controller approach is proposed to improve the control effect for the internal mixer temperature control. The parameters of the neural network are initialized by using the K-means clustering method and the conjugate gradient method is used for optimization training. Examples are provided to illustrate the effectiveness of the proposed method which can improve the control accuracy at the step signal and the sinusoidal signal.