Hybrid yeast strain co-produces isobutanol and ethanol at high yields. Reducing hydrolysis enzyme loading and enhancing xylose conversion greatly impact the economic potential of the biorefinery.

Computer-aided process engineering and conceptual design in energy and chemical engineering has played a critical role for decades. Conventional computer-aided process and systems design generally starts with process flowsheets that have been developed through experience, which often relies heavily on subject matter expertise. These widely applied approaches require significant human effort, either providing the initially drafted flowsheet, alternative connections, or a set of well-defined heuristics. These requirements make the system design highly reliant on the engineer’s experiences and expertise. In this study, a novel reinforcement learning (RL) based automated system for conceptual design is introduced and demonstrated. The RL approach provides a generic tool for identifying process configurations and significantly decreases the dependence on human intelligence for energy and chemical systems conceptual design. An artificial intelligence agent performs the conceptual design by automatically deciding which process-units are necessary for the desired system, picking the process-units from the candidate process-units pool, connecting them together, and optimizing the operation of the system for the user-defined system performance targets. The AI agent automatically interacts with a physics-based system-level modeling and simulation toolset, the Institute for the Design of Advanced Energy System Integrated Platform, to guarantee the system design is physically consistent.

No abstract