Yokogawa's AI Implemented at ENEOS Materials Chemical Facility

ENEOS Materials Corporation and Yokogawa Electric Corporation have disclosed an agreement to implement the Factorial Kernel Dynamic Policy Programming (FKDPP) AI algorithm in an ENEOS Materials chemical facility. This development follows a successful one-year field test where the AI performed well in controlling a distillation column at the facility. This represents a case of reinforcement learning AI officially being employed for direct plant control.

Caption: Desalination columns at the ENEOS Materials chemical plant. Credit: Yokogawa

In a 35-day field test, the AI solution demonstrated control over distillation operations previously managed manually by experienced personnel or by existing control methods (PID control/APC). Despite a scheduled plant shutdown for maintenance, the field test resumed. The AI proved capable of maintaining product quality and liquid levels in the distillation column, while optimizing the use of waste heat.

During the trial, the autonomous control AI demonstrated four significant benefits:

• Consistent operation: The AI exhibited control of liquid levels and maximized waste heat utilization in varied weather conditions.
• Lower environmental impact: By preventing the production of off-spec products, the AI decreased fuel, labor, and other expenses, making efficient use of raw materials. The system also curtailed steam consumption and CO2 emissions by 40% compared to manual control.
• Improved safety and reduced workload: The AI minimized operator intervention, thus reducing the workload, preventing human error, and enhancing safety.
• AI control model: The same AI control model was effectively used even after modifications during a routine shutdown for maintenance and repair.

Caption: Infographic showcasing the various benefits of the test. Credit: Yokogawa

Following the year-long verification process, ENEOS Materials found the AI system to be capable of maintaining stable performance and optimizing operations. The company is considering applying this AI to other processes and plants to enhance productivity and conserve energy.

Yokogawa launched its autonomous control AI service for edge controllers earlier this year. The company offers a global consulting service for customers wishing to achieve autonomous plant operations, covering everything from identifying control issues to calculating cost-effectiveness.

Yokogawa and ENEOS Materials will continue their collaborative efforts to explore digital transformation in plants using AI for control and condition-based maintenance.

Masataka Masutani, Division Director, Production Technology Division, ENEOS Materials Corporation, highlighted the success of the AI in autonomous control of processes previously managed manually.

Further, Kenji Hasegawa, a Yokogawa Vice President and head of the Yokogawa Products Headquarters, expressed his gratitude for being part of the unique autonomization initiative. He highlighted Yokogawa's commitment to developing and expanding the use of autonomous control AI and working with customers to drive decarbonization, digital transformation, and autonomization efforts.