The background of this research is to explore and integrate a range of mechanistic and machine learning based modelling strategies to develop a multilevel digital framework (digital twin) for industrial bioprocess dynamic simulation and prediction, online optimisation (online learning), and product quality control. The framework will effectively rectify and covert low quality industrial plant data into a series of accurate predictive system models for process real-time digitalisation and state estimation. Cutting-edge online optimisation technologies will be also embedded into this framework to further support decision-making during an ongoing process.
In specific, this project aims to address on-line state estimation, one of the primary industrial challenges preventing the continuous manufacturing and product quality control in large scale biochemical processes. Due to the limitation of available measurement facilities, it is not possible to measure important state variables in real time for decision-making. As a result, a reliable state estimator (i.e. predictive process model) becomes a vital tool to observe and regulate ongoing industrial systems. However, conventional physics-based mechanistic models are known to introduce inevitable model-plant mismatch due to the underlying complex microorganism metabolic activities; whilst data-driven models usually lead to unrealistic prediction when extrapolating unknown bioprocess behaviours. To address this challenge, one potential solution is to construct a hybrid model by taking advantage of physical and data-driven modelling techniques. In specific, two different approaches will be investigated in this project. The first one aims to embed a data-driven model to automatically correct the physical model’s model-plant mismatch; whilst the other aims to adopt a data-driven model to identify the most suitable set of parameter values for a mechanistic model at different operating time. Efficiency of the two approaches will be compared through a range of case studies for sustainable biofuels and high-value bioproducts production, and will be verified experimentally with partners in other universities (from the UK and China). 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.