Digital Twinning for Bioprocesses - from Hybrid to Data-Driven Models

Haiting Wang
May 7, 2024 1 min read
My work focus on machine learning applications in surrogate modelling, time series prediction, and reinforcement learning process modelling, scheduling, and optimization of bioengineering, has resulted in a unique framework combining kinetic modelling and machine learning for optimizing dynamic systems. At the same time, we apply a novel offline RL framework for optimal bioprocess production scheduling. In contrast to the traditional RL algorithms like temporal difference (TD) learning, we utilise the transformer model to treat the sequential decision-making process through sequential modelling.

[1] Zhang, D., & del Río Chanona, E. A. (Eds.). (2023). Machine Learning and Hybrid Modelling for Reaction Engineering: Theory and Applications. Royal Society of Chemistry. https://doi.org/10.1039/9781837670178

[2] Wang, H., Kontoravdi, C., del Rio Chanona, E. A. (2023). A Hybrid Modelling Framework for Dynamic Modelling of Bioprocesses. In A. C. Kokossis, M. C. Georgiadis, & E. Pistikopoulos (Eds.), Computer Aided Chemical Engineering (Vol. 52, pp. 469-474). Elsevier. https://doi.org/10.1016/B978-0-443-15274-0.50075-5

Haiting Wang
Haiting Wang
Hybrid modeling for bioprocesses - merging first principles and machine learning

Haiting is a PhD candidate specializing in Digital Twinning for bioprocesses, incorporating hybrid and data-driven models. Her research emphasizes machine learning applications in surrogate modelling, time series prediction, and reinforcement learning for process modelling, scheduling, and optimization in bioengineering. This work has led to a novel framework that merges kinetic modelling with machine learning to optimize dynamic systems. Before her PhD, she was an undergraduate student at Dalian University of Technology and University of Manchester in Chemical Engineering.