Artificial intelligence-driven platform for catalytic reactor discovery and optimization applied to carbon dioxide valorization

Digital technologies, including artificial intelligence and advancements in additive manufacturing, have revolutionized all areas of chemistry and chemical engineering. In the field of reactor engineering, improved performance has been enabled through the development of novel geometries. However, until now, design has largely been reliant on human input. A digital platform, Reac-Discovery, is introduced in this study, which integrates the generation, fabrication, and optimization of catalytic reactors based on periodic open-cell structures (POCs). The parametric design and analysis of advanced structures from mathematical models (Reac-Gen) are integrated with high-resolution 3D printing and functionalization of catalytic reactors (Reac-Fab), along with an algorithm that validates the printability of reactor designs and a self-driving laboratory platform (Reac-Eval) capable of parallel multi-reactor evaluations featuring real-time NMR monitoring and machine learning (ML) simultaneous optimization of process parameters and topologic descriptors. Reactor designs and reaction conditions can be iteratively, dynamically, and rapidly refined by Reac-Discovery, enabling the discovery of optimal geometries for industrially relevant processes. The heterogeneously catalyzed CO₂ cycloaddition at low pressure was chosen as a benchmark reaction. An improvement of approximately one order of magnitude over the state of the art was offered by Reac-Discovery. A transformative framework for advancing complex chemical systems is established by seamlessly integrating digital design and machine learning through Reac-Discovery.

• Tinajero, C
• Zanatta, M
• Garcı́a-Verdugo, E
• Sans, V

• Universitat Jaume I

• Request a Brochure
• Request more Info
• Request a Quote