Aramco’s Fadhili gas plant
The AI system, developed by Yokogawa, applies the Factorial Kernel Dynamic Policy Programming (FKDPP) reinforcement learning algorithm. It uses multiple coordinated AI agents to autonomously control and optimize acid gas removal (AGR) operations within the plant. The project was introduced in three stages, gradually optimizing different parts of the AGR process before achieving full autonomous control of its core operations.
To ensure safety and reliability, Yokogawa first built a detailed simulator of the plant for AI agent training, followed by extensive validation tests. After confirming stable performance, the AI system was integrated into Yokogawa’s CENTUM VP integrated production control system, which leverages existing plant safety features. Early evaluations at the Fadhili Gas Plant have shown promising results, including a 10–15% reduction in amine and steam usage, about 5% lower power consumption, improved process consistency, and a marked decrease in manual operator interventions, even under changing environmental conditions.
Aramco Engineering Services Senior Vice President Khalid Y. Al Qahtani stated: “Aramco has embarked on an ambitious plan to unlock value by deploying a wide range of industrial AI applications across our operations. The collaboration with Yokogawa is one of many initiatives that focus on improving efficiency, enhancing sustainability, and generating more value for our shareholders. It 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. We look forward to building on this important milestone, as we explore further adoption of cutting-edge solutions that will contribute to a new era of industrial innovation.”
Yokogawa’s Director, President & CEO, Kunimasa Shigeno, added: “We are honored that Yokogawa was entrusted by Aramco to implement such ground-breaking technology in one of its major facilities. We are very pleased that the results have already exceeded expectations. Yokogawa is advocating the transition from industrial automation to industrial autonomy (IA2IA), and this deployment proves that we are ready to lead the way towards safe and secure autonomous operations for plants in the energy sector.”
Yokogawa defines autonomous control AI as systems capable of independently determining optimal control methods and adapting robustly to unforeseen situations. The FKDPP algorithm, developed jointly with the Nara Institute of Science and Technology, won Japan’s 2023 Prime Minister’s Prize for Industrial Technology.
Through this achievement, Yokogawa and Aramco have demonstrated how advanced AI integration can transform energy sector operations, advancing efficiency, sustainability, and industrial autonomy.
