TOKYO – May 24, 2024 – ENEOS Corporation (ENEOS) and Preferred Networks, Inc. (PFN)　announced today that they started continuous autonomous operation of an atmospheric distillation unit for processing crude oil in January 2024.The atmospheric distillation unit currently operated autonomously with an AI system is located in the ENEOS Kawasaki Refinery.

Jointly developed by ENEOS and PFN, the AI system automates large-scale, complex operations of oil refinery plants that required human operators with years of experience. Since 2018, ENEOS and PFN have been co-developing AI systems for improving safety and stability of plant operations by reducing dependence on technicians’ varying skill levels.

With 24 key operational factors to control and as many as 930 sensors to monitor, the atmospheric distillation unit especially requires a high level of skills and experience. AI-based, continuous autonomous operation of an atmospheric distillation unit is the world’s first according to a consulting firm Globe-ing Inc.

The AI system for the atmospheric distillation unit continuously monitors 24 key operational factors and adjusts 13 valves at the same time to stabilize fluctuations resulting from crude oil switching as well as changes in crude oil throughput. The AI system has demonstrated higher stability and efficiency compared with manual operations.

ENEOS and PFN plan to deploy the co-developed AI systems to other ENEOS refineries and later provide them as a packaged solution to external parties as well.

Through this collaboration, ENEOS and PFN will also support the United Nations’ Sustainable Development Goals including Goal 9 (“Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation”).

Note: July 2023 news release from ENEOS and PFN:
ENEOS and PFN Begin Continuous Operation of AI-Based Autonomous Petrochemical Plant System

Atmospheric distillation unit in ENEOS Kawasaki Refinery

AI system for autonomous plant operation

Stability of key operational factor (product property value) and control achieved by
AI-based autonomous plant operation system

(Also included in the July 2023 announcement on the continuous autonomous operation of a butadiene extraction unit)

The AI system successfully controls the stability even under external disturbances by
maintaining the key operational value close to the target value.

AI-based autonomous operation system’s control during crude oil switching

The AI system successfully controls the stability even during crude oil switching operations.