t cht lk
“
THE DEVELOPMENT OF HYBRID MODEL SOLUTIONS WILL ALSO , FOR MANY REFINERS , BE THE FIRST STEP IN REALISING THE VISION OF THE SELF-OPTIMISING PLANT .
has not yet fully realised the potential of Industrial AI .
That is largely because Machine Learning and AI are frequently locked in isolation today , rather than being combined with existing engineering capabilities – tools , models and expertise – to deliver a practical solution that effectively optimises refinery assets .
These are assets that typically rely on engineering models built from the ‘ first principles ’ ( or fundamental basics ) of chemistry and physics , which incorporate key domain knowledge such as process safety and understanding of the industry ’ s complex systems .
These models draw on the expertise and experience of the world ’ s foremost scientists , process engineers and operators .
They are highly accurate but have limitations in certain processes , to enhance their accuracy , plant data must be employed to calibrate them to observed plant conditions and performance .
Currently , effective model calibration requires significant understanding and experience .
Building a hybrid model
This is where AI and Machine Learning have a key role to play . These technologies are fast emerging as tools that can greatly accelerate the ability to employ plant data , both to calibrate first-principles models and to quickly create data-based models of processes and phenomena . AI has the potential to lower the expertise required to model process systems , but it must be combined with domain expertise to create the real-world ‘ guardrails ’ that allow it to work safely , reliably and intuitively .
This combination enables what we call ‘ hybrid models ’, which effectively bring together AI and first-principles to deliver a comprehensive , accurate model more quickly and without requiring significant expertise . And crucially , they serve as a vital staging post on the way to the self-optimising plant .
Machine Learning is used to create the model , leveraging simulation , plant or pilot plant data . The model also uses domain knowledge , including first principles and engineering constraints , to build an enriched model – without requiring the user to have deep process expertise or be an AI expert .
The solutions supported by hybrid models act as a connection point between the first principles-focused world of today and the ‘ smart refinery ’ environment of the future . They are the essential driver of the selfoptimising plant .
Many companies today are already experiencing the benefits of a hybrid modelling approach . Refining and olefin margins are closely related to plant planners ’
78 INTELLIGENTCIO www . intelligentcio . com