Emerson & Aramco: Using AI to Improve Refining Efficiency

Emerson has introduced an advanced AI-powered optimisation solution for Aramco, one of the world’s leading integrated energy and chemicals companies, in a move designed to strengthen efficiency across global refining operations.

At the core of the initiative is the integration of Emerson’s Aspen Hybrid Models into Aramco’s refinery planning systems, forming one of the most extensive multi-site, multi-period optimisation frameworks in the energy sector.

By combining first-principles engineering models with industrial AI and deep operational expertise, the solution captures complex relationships in yield and product quality.

This has enabled prediction accuracy of up to 98.5% in critical refinery units, supporting more reliable and data-driven decision-making across refining assets.

Expanding AI in refining operations

Aramco has deployed the hybrid models across Continuous Catalyst Regeneration (CCR) and Platformer Units, where they are enhancing feedstock blending strategies, tightening alignment between planning and execution and improving margin forecasting across its global refining portfolio.

The company is now extending the approach to hydrocracker units, a step expected to further improve predictive accuracy while demonstrating how scalable AI-led optimisation can support increasingly complex energy systems.

"This deployment represents a significant milestone in Aramco's AI strategy and our long-standing relationship with Emerson," says Ahmad Alkudmani, Director of the Global Optimiser Department at Aramco.

"We are committed to leveraging innovative technologies for smarter, more efficient refining optimisation. With improved model accuracy, we are enhancing planning decisions, reducing manual adjustments and uncovering new value across our global assets."

The implementation delivers measurable gains across refinery performance.

High prediction accuracy is helping to increase yields and improve product quality across varied feedstocks, operating conditions and throughput levels. At the same time, optimised blending strategies are enabling more flexible feedstock selection, supporting both profitability and sustainability objectives.

Improving efficiency across energy assets

A key advantage of the system is its ability to reduce discrepancies between planning models and real-world plant performance, limiting the need for manual intervention.

Greater model precision allows operators to better capture non-linear dynamics in complex processes such as reactor operations, while automation reduces the need for continuous manual tuning. This contributes to stronger operational efficiency across refining activities.

The solution is also designed for scale, maintaining performance across a wide range of refinery configurations globally.

Aramco is deploying Aspen Hybrid Models through Emerson’s AspenTech Performance Engineering and Manufacturing and Supply Chain suites, enabling highly detailed nonlinear optimisation based on thousands of simulation scenarios calibrated with real plant data.

This reflects a broader shift in the energy industry, where AI is increasingly being combined with established engineering principles to address operational complexity and improve asset performance.

Bridging AI and energy expertise

Success in CCR and Platformer Units is providing a foundation for wider rollout across refining operations, highlighting the growing role of hybrid AI models in modern energy systems.

"Aramco continues to set the standard for operational excellence through digital innovation," adds Claudio Fayad, CTO of Emerson's Aspen Technology business.

"This deployment of AI-driven Aspen Hybrid Models to optimise complex, multi-site, multi-period planning workflows demonstrates the tangible value of combining deep domain expertise with advanced AI.

"We're excited to expand our strategic relationship with Aramco as they advance their digital transformation goals."

The collaboration highlights how AI-driven solutions are reshaping refinery planning and execution.

As deployment expands across additional units and facilities, the approach could redefine efficiency benchmarks in global refining, strengthening the connection between digital modelling and real-world energy operations.