Hybrid physics-based and data-driven modelling for bioprocess online simulation and optimisation.

Model-based online optimisation has not been widely applied to bioprocesses due to the challenges of modelling complex biological behaviours, low-quality industrial measurements, and lack of visualisation techniques for ongoing processes. This study proposes an innovative hybrid modelling framework which takes advantages of both physics-based and data-driven modelling for bioprocess online monitoring, prediction, and optimisation. The framework initially generates high-quality data by correcting raw process measurements via a physics-based noise filter (a generally available simple kinetic model with high fitting but low predictive performance); then constructs a predictive data-driven model to identify optimal control actions and predict discrete future bioprocess behaviours. Continuous future process trajectories are subsequently visualised by re-fitting the simple kinetic model (soft sensor) using the dada-driven model predicted discrete future data points, enabling the accurate monitoring of ongoing processes at any operating time. This framework was tested to maximise fed-batch microalgal lutein production by combining with different online optimisation schemes and compared against the conventional open-loop optimisation technique. The optimal results using the proposed framework were found to be comparable to the theoretically best production, demonstrating its high predictive and flexible capabilities as well as its potential for industrial application. This article is protected by copyright. All rights reserved.