Automated Crystallization Monitoring in Material Development using Computer Vision and Neuronal Networks

Abstract

AbstractCrystallization is critical in producing various substances in the food and pharmaceutical industries. The process begins with nucleation from a supersaturated solution, followed by the directed movement of solute molecules toward the newly formed nuclei. This movement is influenced by different factors such as molecular attraction and thermodynamic properties, which influence the resulting crystal size and shape. This paper presents an automated monitoring approach for the growth process of crystallization from saturated solutions. To monitor such a process, a combination of artificial intelligence and computer vision is used. The approach was developed for application in material research to automate the processing of numerous samples, which would otherwise require laboratory personnel.