Aramco and Yokogawa Commission Multiple Autonomous AI Control Agents at Major Gas Facility

Yokogawa, a leader in process automation technology, announces it has achieved a historic milestone in the deployment of industrial artificial intelligence (AI) solutions with Aramco, one of the world’s leading integrated energy and chemicals companies. Multiple autonomous control AI agents have been successfully implemented by Yokogawa at Aramco’s Fadhili Gas Plant in the Kingdom of Saudi Arabia to enhance operational efficiency.

The AI solution developed by Yokogawa uses multiple, coordinated AI agents of the Factorial Kernel Dynamic Policy Programming (FKDPP) reinforcement learning-based AI algorithm to directly and autonomously control and optimize acid gas removal (AGR) operations at the Fadhili Gas Plant.

The solution was introduced in three phases, progressively optimizing various sections until autonomous control of the core process in the AGR unit was achieved. To ensure safety, Yokogawa first created a simulator of the plant to train AI agents, and then evaluated their reliability and validity. Subsequently, they were integrated with Yokogawa's CENTUM VP integrated production control system to leverage the safety functions of the existing plant.

Implementation is currently undergoing a detailed evaluation, but initial results from Fadhili Gas Plant demonstrate a 10% to 15% reduction in its amine and steam usage, around 5% reduction in power usage, improved process stability, and a significant decrease in operator manual intervention, despite ambient condition changes.