Data-driven inverse design for magnesium hydroxide precipitation: Coupling CFD–PBM with deep learning to control hexagonal platelets morphology formation and particle size distribution

Key Points

• This research aims to optimize the formation of magnesium hydroxide by controlling the morphology and size of particles.
• Developed a data-driven inverse design approach combining computational fluid dynamics (CFD) and population balance modeling (PBM).
• Utilized deep learning to predict and control the morphology and particle size distribution during magnesium hydroxide precipitation.
• Successfully controlled hexagonal platelet formation, achieving desired morphology and size distributions.
• Demonstrated improved particle size distribution with a coefficient of variation reduced to 12%.