Navigating industry 4.0 and 5.0: the role of hybrid modelling in (bio)chemical engineering's digital transition

This work investigates the potential of hybrid modelling in the digitalization of the chemical and biochemical industries. Hybrid modelling combines first-principles with data-driven models and is a vital enabler for the knowledge-informed transition to Industry 4.0 and, ultimately, 5.0. By integrating data with mechanistic know-how, hybrid modelling facilitates the implementation of "smart manufacturing". Although there have been many innovations in the field of machine learning, AI, and cloud computing, the industry is still some distance away from becoming truly digital; this is particularly true in the case of the biochemical industry, which in many ways still is in the industry 3.0 stages. This gap hinders the full realization and benefits of the digital transition, such as easier process optimization, better cost-efficiency balance, and overall improved competitiveness and sustainability. This research delves into documented examples of hybrid modeling in chemical and biochemical engineering research and industries. It aims to illustrate current motivations, implementation challenges, and practical issues that hybrid modeling can address. The goal is to derive the path towards fully implementing hybrid modeling as an effective tool and key enabler for creating true digital twins and successful digitalization.