The AI solution is autonomously optimizing the critical Acid Gas Removal (AGR) unit, yielding significant reductions in energy and chemical consumption while improving process stability.
In a significant leap towards industrial autonomy, Yokogawa Electric Corporation and Aramco have announced the successful deployment and commissioning of multiple autonomous control AI agents at Aramco’s Fadhili Gas Plant in the Kingdom of Saudi Arabia. This groundbreaking implementation is already delivering substantial efficiency gains in the plant’s crucial gas treatment operations.
The cutting-edge solution uses multiple, coordinated AI agents based on the Factorial Kernel Dynamic Policy Programming (FKDPP) reinforcement learning algorithm—a technology jointly developed by Yokogawa and the Nara Institute of Science and Technology (NAIST). These agents are designed to directly and autonomously control and optimize the Acid Gas Removal (AGR) operations at the Fadhili Gas Plant.
Initial results from the Fadhili Gas Plant’s implementation phase are exceeding expectations, demonstrating a 10% to 15% reduction in amine and steam usage, a roughly 5% reduction in power usage, and a significant decrease in the need for operator manual intervention. These improvements were achieved despite changes in ambient operating conditions, highlighting the robustness of the autonomous system.
Safety was a paramount concern throughout the deployment process. Yokogawa adopted a meticulous three-phase approach, beginning with the creation of a plant simulator to train and rigorously evaluate the AI agents for reliability and validity. Only after successful simulation were the agents integrated with Yokogawa's CENTUM VP integrated production control system, ensuring that the existing plant safety functions remained fully leveraged. The phased roll-out progressively optimized various sections until full autonomous control of the AGR unit’s core process was achieved.
This landmark deployment is a key part of Aramco's wider ambition to harness industrial AI applications across its operations to improve efficiency, enhance sustainability, and generate greater value.
Khalid Y. Al Qahtani, Aramco Engineering Services Senior Vice President, emphasized the company’s commitment to technological leadership, stating, "The collaboration with Yokogawa is one of many initiatives that focus on improving efficiency, enhancing sustainability, and generating more value for our shareholders." He added that the achievement "reflects how the company is harnessing advanced technology, including AI, to elevate its performance and reinforce its position as a technology leader in the energy sector."
Kunimasa Shigeno, Director, President & CEO, and Representative Executive Officer of Yokogawa Electric, heralded the milestone as a pivotal moment in the transition from Industrial Automation to Industrial Autonomy (IA2IA). "We are very pleased that the results have already exceeded expectations," he remarked. "This deployment proves that we are ready to lead the way towards safe and secure autonomous operations for plants in the energy sector."
