Japan synthetic rubber maker advances “world first” AI production

Tokyo – ENEOS Materials Corp. is to adopt an advanced AI control technology under an agreement with control & automation major Yokogawa Electric Corp., the companies announced 30 March.

The deal, they said, will see a 'reinforcement learning-based AI algorithm' called ‘factorial kernel dynamic policy programming’ (FKDPP) officially adopted for use at an ENEOS Materials production plant.

The move follows field testing in which the autonomous control AI “demonstrated a high level of performance while controlling a distillation column at this plant for almost an entire year.”

According to the companies, ENEOS Materials’ decision is the first example in the world of reinforcement learning AI being formally adopted for direct control of a plant.

Over a 35-day consecutive period, from 17 Jan to 21 Feb, 2022, the field test confirmed that the AI solution could control distillation operations that were beyond the capabilities of existing control methods.

Following a scheduled plant shutdown for maintenance and repairs, the field test resumed and has continued to the present date, the companies’ statement continued.

“It has been conclusively shown that this solution is capable of controlling the complex conditions that are needed to maintain product quality and ensure that liquids in the distillation column remain at an appropriate level.”

This was achieved “while making maximum possible use" of waste heat as a heat source even in winter and summer weather, with temperature changes of around 40 degrees C.

“In so doing, it stabilised quality, achieved high yield, and reduced steam consumption and CO2 emissions by 40% in comparison to conventional manual control.”

By eliminating the production of off-spec products, the autonomous control AI reduced fuel, labour, and other costs, and made efficient use of raw materials, the companies added.

Even after modifications were made at the plant during a routine shutdown for maintenance, the same AI control model could remain in use, they further noted.

ENEOS Materials now aims to apply AI to other types of processes and plants, and continue to improve productivity and save energy by expanding the scope of autonomisation.

“This system can operate stably without being affected by seasonal changes or regular maintenance and repairs, and can save energy and reduce GHG emissions," said Masataka Masutani, division director, production technology, at ENEOS Materials.

“Through smart production, we will continue to strive for safety and stability, decarbonise operations, and enhance competitiveness,” added Masutani.

“The fact that this field test confirmed the model's ability to be applied as is even after the performance of regular maintenance implies the robustness of the AI control model,” noted Takamitsu Matsubara, Professor at the Nara Institute of Science and Technology:

“I believe that FKDPP is a new control technology that can handle complex conditions, will make broad-ranging contributions to the development of industry around the world,” concluded Matsubara.

Formed in April 2022, through ENEOS Corp.’s acquisition of JSR's elastomers business, ENEOS Materials manufactures synthetic rubber, thermoplastic elastomers, latex, and other raw materials.