CPACT Webinar on
Computational Design Intelligence for
Chemical Engineering
Nausheen Basha, University of Manchester
22nd October 2026 at 3pm (UK time)
Designing next-generation flow reactors and multiphase
devices within chemical and process industries, requires navigating complex
geometry spaces where small shape changes can strongly affect transport,
mixing, interfacial dynamics, and product quality. We develop an
‘Optimise-Predict-Accelerate’ framework combining geometry representation
learning, geometry-conditioned generative modelling, multi-fidelity modelling,
and Bayesian optimisation. Compact latent representations enable efficient
exploration of design spaces, while multi-fidelity surrogates reduce reliance
on expensive high-fidelity computational fluid dynamics models.
Geometry-conditioned generative models further predict transient physical
states across unseen designs. The framework provides a general route to
accelerated, physics-aware design for pharmaceutical applications including
continuous manufacturing, crystallisation, emulsification, particle formation,
lipids processing, and spray-based drug-product technologies.
This webinar
will last no longer than one hour.
The webinar
is for CPACT members only and is free to attend.
Please
register directly at https://universityofstrathclyde.webex.com/weblink/register/r6a383c86233a0756e89f4891b0c8580b