About the Project
Designing industrial scale reaction systems and unit operations takes a sophisticate procedure and involves a range of multiscale modelling and experimentation steps. This is often time consuming and results in the generation of abundant data sets across both spatial and temporal dimensions. Traditionally, these data sets are analysed to create a set of constitutive equations (empirical physical laws) to estimate impact of fluid dynamics and unit operation’s geometry on the system’s performance. However, this procedure requires substantial experience (prior knowledge) and usually lacks of theoretical support. One potential approach to address this issue through a more systematic manner is to apply the emerging Deep Learning technologies arising from the AI community, including Ensemble Learning and Deep Neural Networks. These techniques offer several significant advantages compared to the conventionally used unsupervised learning and statistic methods for multivariate data analysis.
This project aims to adopt Deep Learning methods to identify most influential factors for unit operation scale-up, and to exploit data-driven based model structure detection strategies to automatically construct new constitutive relations for large scale photobioreactor design. Time-series events and bioprocess kinetics will be particularly considered to extend applications of Deep Learning models into bioreaction system dynamic modelling. This project will provide valuable suggestions to advance the future design of innovative photobioreaction systems. This study will be conducted under collaborations with universities in the UK, China, and South Africa. A brief introduction to the research group can be found through the following link:
Candidates are expected to hold or achieve a first class or 2:1 honours degree (or equivalent) in Chemical Engineering, Process Systems Engineering, Biochemical Engineering, Industrial Engineering, Mathematics, Computer Science or other related area. Students with a solid mathematical background are particularly welcome. A prior knowledge/experience in mathematical programming and optimisation theory is desirable.