Skill-based PID control by using neural networks

TLDR: The self-tuning neural-PID control method, which has the characteristic of tuning PID gains automatically by neural networks, is used to improve the control performance of the temperature in the batch reactor.

Abstract: This paper describes a new PID control scheme by using neural networks. This control method enables a plant to operate smoothly under various conditions. We focuses on the temperature control for a chemical plant which produces polyethylene in a batch reactor. Here, the reaction in a tank is complex and has many nonlinear factors. The temperature control is realized by valves manipulation. Since the valve control have been performed by using a conventional PID controller, it generally needs much effort and time to tune the PID gains. Thus, in the production field, a new control system with a cheap and simple structure is needed to tune PID gains without operator's decision under various conditions of the plant. For that purpose, we use the self-tuning neural-PID control method which has the characteristic of tuning PID gains automatically by neural networks. From the experiment results, we show the effectiveness of the proposal method to improve the control performance of the temperature in the batch reactor.