The application of fuzzy neural networks to the temperature control system of oil-burning tunnel kiln

Fuzzy control is a human-imitating control technique which is independent of the mathematical model of plants. It utilizes priori knowledge to carry out approximate reasoning. However, it lacks the abilities of self-tuning or self-learning in industrial applications. The temperature control process of an oil-burning tunnel kiln is a multivariable and nonlinear dynamic system. This paper presents a fuzzy neural network control strategy which is able to enhance the capacity of self-learning of fuzzy control rules, based on the self-learning ability of neural networks. Simulation research and a physical analog experiment prove the feasibility of this control strategy.

[1]  Sigeru Omatu,et al.  Process control by on-line trained neural controllers , 1992, IEEE Trans. Ind. Electron..

[2]  E. S. Plumer.  Time-optimal terminal control using neural networks , 1993, IEEE International Conference on Neural Networks.

[3]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[5]  K.S. Narendra,et al.  Intelligent control using neural networks , 1992, IEEE Control Systems.

[6]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[7]  Derrick H. Nguyen,et al.  Neural networks for self-learning control systems , 1990 .