Hybrid Modeling of Chromatographic Systems

Chromatography is the workhorse in biologics manufacturing processes, where its performance significantly contributes to the quality outcomes of the batch, and therefore must be carefully controlled. Process modeling and simulation is the best way to provide control to the process. This proposal aims to develop a hybrid chromatography modeling approach, utilizing state-of-the-art machine learning method, combines both first principal knowledge and data-driven sights to improve the speed and accuracy of chromatography modeling. The partner organization will be able to develop expertise in hybrid chromatography modeling and will be able to use the models to provide insights in process optimization, monitoring and control. The benefits range from significant savings in materials and time to expediting regulatory approval of life-saving vaccines.

Faculty Supervisor:

Vinay Prasad;Zukui Li;Arvind Rajendran

Student:

Partner:

Sanofi

Discipline:

Engineering

Sector:

Health and Related Sciences & Technology; Manufacturing; Other services (except public administration); Professional, scientific and technical services; Wholesale trade

University:

University of Alberta

Program:

Accelerate