Efficient process optimization for a circular economy by full flowsheet neural networks
Kärkäs V, Kircher T, Hungsberg M, Votsmeier M, Etzold B (2025)
Publication Type: Journal article
Publication year: 2025
Journal
Original Authors: 5
Pages Range: 121784
Article Number: 121784
DOI: 10.1016/j.ces.2025.121784
Abstract
The transition of the chemical industry to a circular economy brings challenges, including fluctuating feedstock compositions and volatile energy prices, which necessitate efficient process optimization. Process flowsheet simulations, invaluable in process design, struggle with high-dimensional optimization due to computational cost and lack of gradient information. We address this by combining neural network surrogate models with gradient-based optimization and explainable AI analysis to enable high-throughput flowsheet optimization. Using a polymer waste-to-methanol process as a case study, neural network inference of the process response is 50,000 times faster than conventional flowsheet simulations. Shapley Additive exPlanations (SHAP) provide insights into the contributions of feedstock compositions and process parameters on process responses and gradient-based optimization optimizes flowsheets within 0.35 s. The optimized process aligns with industry heuristics, achieving syngas ratios near the theoretical optimum. This approach accelerates optimization, provides valuable insights into high-dimensional flowsheets, and advances efficient process design in a circular economy.
Authors with CRIS profile
Ville Kärkäs
Lehrstuhl für Power-to-X-Technologien
Bastian Etzold
Lehrstuhl für Power-to-X-Technologien
Involved external institutions
Germany (DE)How to cite
APA:
Kärkäs, V., Kircher, T., Hungsberg, M., Votsmeier, M., & Etzold, B. (2025). Efficient process optimization for a circular economy by full flowsheet neural networks. Chemical Engineering Science, 121784. https://doi.org/10.1016/j.ces.2025.121784
MLA:
Kärkäs, Ville, et al. "Efficient process optimization for a circular economy by full flowsheet neural networks." Chemical Engineering Science (2025): 121784.
BibTeX: Download