Application of neuro-fuzzy hybrid control system to tank level control

The authors propose a practical control method using neural networks and fuzzy control techniques, whereby neural networks estimate the target of fuzzy control. Neural networks estimate the transient state of a plant which has a nonlinear process such as refrigeration and filtering. Based on the estimation, a suitable control target pattern for fuzzy control is selected. This method has been applied to the tank level control problem of a solvent dewaxing plant. It is shown that the system can control the tank level effectively not only in the steady state but also in the transient state