A novel surrogate-based optimisation framework for pharmaceutical process systems

The pharmaceutical sector increasingly depends on advanced process modelling techniques to streamline drug development and manufacturing workflows. Utilising these models for optimisation, can drive substantial improvements in operational efficiency, cost reduction, and adherence to stringent product quality standards. However, the complexity or high computational demands of such models often necessitate alternative approaches, with surrogate-based optimisation emerging as a practical and efficient solution. In this study, a framework is presented that integrates multiple software tools into a unified system for employing surrogate-based methods to tackle the challenges associated with optimising complex system models that represent real-world processes. The approach focuses on multi-objective optimisation to improve key metrics such as yield, purity, and sustainability, while utilising pareto fronts to visualise and navigate trade-offs between competing objectives effectively. The findings indicate that surrogate models can effectively approximate complex behaviours, providing a practical approach to robust optimisation of an Active Pharmaceutical Ingredient manufacturing flowsheet. Specifically, the single-objective optimisation framework achieved a 1.72% improvement in Yield and a 7.27% improvement in Process Mass Intensity, while the multi-objective optimisation framework managed to achieve a 3.63% enhancement in Yield while maintaining high purity levels.