化学反応装置用ニューロコントローラの開発研究

概要

論文の詳細を見る
The purpose of this study is to develop a mu1ti-functional automated process contoller for use in a synthesis system of chemical reactions. Chemical reactions can be very complex， making it difficult to control the reaction temperature. In this research， a neura1 network is proposed for controlling the temperature of the reaction. First， a neural network controller is constructed to regulate the temperature of the chemical reaction， and then its effectiveness is tested throughexperiments. Next, a neural network diagnostic system is proposed in the event of machine trouble or human error. A new type of chemical conversion estimation is also proposed from these results. Finally，it is verified that it can efficient1y control the chemical reaction using developed AI process controller.
福井大学工学部の論文