Overview

Orbital is the first foundation model purpose-built for energy operations. It combines three powerful models: a time series model, a physics-based model, and a language model trained on decades of chemical and process engineering expertise. These models work in parallel, reinforcing each other, continuously retrieving and interpreting operational data in real time. Orbital returns insights in natural language that are fast, accurate, and grounded in real-world physics, process and chemical engineering.

Applications include:

• Energy Intensity – Measures operational trade-offs in real time to reduce energy per unit of output without impacting production
• Process Reliability – Detects early signs of process drift across key variables, helping teams act sooner and bring units back to baseline before failure
• Process Optimisation – Recommends real-time changes to feed blend, reactor temp, and cut points to improve quality and reduce off-spec
• Carbon Intensity – Tracks CO2 and hydrogen flows to spot reuse and recovery opportunities, improve separation, and reduce emission

Speakers

Dan Jeavons, Applied Computing

Dan is an experienced energy executive and visionary in AI. At Shell, he led all global AI and data science efforts. His industry leading work in digital transformation has been recognised by his listing in the BT150.

Sam Tukra, Applied Computing 

Sam is an expert in Computer Vision, NLP, and Reinforcement Learning, and has published papers in high-impact conferences like CVPR and IEEE-PAMI. He has also led AI teams at Hitachi and Shell.

The material presented has not been peer-reviewed. Any opinions are the presenter’s own and do not necessarily represent those of IChemE or the Process Management & Control SIG. The information is given in good faith but without any liability on the part of IChemE.

Find out more about Applied Computing.

Time

10:00–11:00 BST.

Software

The presentation will be delivered via Microsoft Teams. We recommend downloading the app from the Microsoft website, rather than using the web portal.