PID gain tuning method for oil refining controller based on neural networks

In these years, plant control systems are highly automated. It is unavoidable that control performances change with the passage of time, so it is necessary to tune control parameters. In this study, PID control system for oil refining chemical plant process is treated. In the oil refining facilities, there are thousands of control loops in the plant to keep the product qualities at desired values and to secure the safety of the plant operation. According to the ambiguity of the interferences between control loops, it is difficult to estimate the state of plant dynamics accurately. Neuro emulator is employed to estimate the plant characteristics. As for the method of PID gain tuning, a recurrent type neural network (RNN) is employed. Combining neuro emulator and RNN model, an auto tuning system of PID control gains has been constructed. Through numerical experiments using actual plant data, the effect of the proposed method was ascertained. Further, operator's guidance system for PID gain tuning was developed.