Data-driven model predictive control for pharmaceutical continuous manufacturing

This study demonstrates that developing interpretable, data-driven models for pharmaceutical continuous manufacturing is feasible using a machine learning method called Dynamic Mode Decomposition with Control (DMDc). This approach facilitates adoption within Good Manufacturing Practice (GMP)-regulated areas of the pharmaceutical industry. Furthermore, since the pharmaceutical industry needs to be more operationally efficient to be profitable and sustainable, we present a real-time monitoring strategy framework using an interpretable DMDc dynamic model in the design and tuning of a model predictive control (MPC) system for granule size control during a twin-screw granulation process. This model exhibited low computational complexity without requiring first principles knowledge, while effectively capturing nonlinear dynamics of this Multiple input multiple output (MIMO) system, with better performance (e.g., r2 > 0.93 vs.0 for D50 predictions) in the reconstruction of unseen test data in comparison with benchmark data-driven methods for system identification. The DMDc-MPC was implemented and tested on setpoint tracking and disturbance rejection and the proposed advanced process control framework guaranteed both.