2025 - AVEVA World - San Francisco - Energy (Oil, Gas & New Energies)
Accelerating Corporate Decision-Making with the Process Simulation Twin
Abstract: In the refining industry, timely decisions are paramount, as delays can significantly impact profitability. Effective decision-making relies heavily on simulation, which facilitates outcome prediction, scenario evaluation, and bottleneck identification – ultimately guiding investment, maintenance scheduling, and production planning. Traditional simulation approaches, however, are often hampered by lengthy setup processes, delaying critical decision-making. To address this challenge, Saudi Aramco developed the Process Simulation Twin (PST), an innovative application that automates data collection, reconciliation, and model calibration to provide an up-to-date, refinery-wide simulation framework for techno-economic assessment. By leveraging the PST, users gain instant access to current process simulations and can focus on higher-value activities, such as troubleshooting operational issues and opportunity identification. The PST offers consistent, real-time estimates for immeasurable key performance indicators (KPIs), monitors planning model accuracy, and provides regular planning model updates. Furthermore, it lays the groundwork for integrating Artificial Intelligence (AI) and Machine Learning (ML) techniques, including reinforcement learning and predictive analytics, to drive informed decision-making and unlock sustainable value creation across the organization.
Industry
Oil Gas and Energy
Company
Saudi Aramco
Speaker
Gabriel Winter
Gabriel Winter is seasoned professional with over two decades of experience in process engineering, process modeling, and optimization. Currently, he leverages his expertise as an Engineering Specialist at Aramco, focusing on advanced Digital Twin & Optimization technologies. Prior to Aramco, Gabriel's experience encompassed roles at AspenTech, KBC Advanced Technology, and Stone & Webster. In these positions, he aided clients in implementing various process modeling and optimization solutions and honed his skills as a process engineer. Gabriel holds a B.S. degree in Chemical Engineering from The University of Texas at Austin
Session Code
SESS-72
