ENEOS and PFN pass trial at AI-controlled petrochemical plant

The project lasted two days and consisted of monitoring important factors and adjusting valves based on simulated data processed by the system.

ENEOS Corporation and Preferred Networks, Inc. announced that they have successfully operated a stand-alone butadiene extraction unit at the ENEOS Kawasaki refinery petrochemical plant for two consecutive days using a new intelligence system artificial. The system, which was jointly developed by the two companies, automates large-scale and complex operations at oil refineries and petrochemical plants that currently require skilled operators.

The AI ​​was designed to predict future unit sensor values ​​and valve operating requirements based on past data of complex correlations between multiple similar values ​​generated via simulated data. The trial lasted for two days, during which time the system managed to monitor 25 important factors including internal temperature, pressure, flow rate and product conditions, and autonomously adjust 12 valves in the unit. extraction of butadiene.

Both companies expect the AI ​​system to help improve the safety and stability of plant operations by reducing reliance on different skill levels of operators. Its development is supported by 2020 grants from the Japanese Ministry of Economy, Trade and Industry.

The trial will continue to achieve stable operations and expand its use to other major plant units, including same-site crude stills and other refineries. Following the success of its joint venture, ENEOS and PFN plan to implement a new AI-based autonomous factory operating model to increase production and energy efficiency.

Associated content

To discuss

Comments are closed.