Sensitivity analysis and multi-objective optimization for design guideline of effective direct conversion of CO2 to DME

Carbon capture, utilization and storage (CCUS) technologies can play an important role in sustainable development and climate change mitigation. After capture, carbon dioxide can be used to produce valuable chemicals such as dimethyl ether (DME). The direct synthesis of DME from CO2 involves a complex reaction usually carried out on a CuO-ZnO-Al2O3/gamma-Al2O3 catalyst, which can be operated under various temperature, pressure, and feed conditions. Optimizing DME production is a challenging task and warrants thorough investigation. A pseudo-homogeneous mathematical model was developed to describe the behavior of this reaction in a fixed bed reactor. This model was validated with experimental data from the literature and used to provide valuable insights regarding the effects of operating conditions on the yield and selectivity of DME and methanol, as well as on CO2 conversion. Given the numerous interdependent variables influencing the process, the task of exploring various operating conditions was accomplished using deep neural network (DNN)-based surrogate modeling, significantly reducing computational efforts. Using the surrogate models, multi-objective optimizations were performed with non-dominated sorting genetic algorithm-II (NSGA-II) to establish design guidelines. Results have shown that DME yield is improved by the presence of CO in the feed, and that the optimal operating temperature varies with the operating pressure. Additionally, the H-2/CO2 feed ratio has a minor impact on DME formation, though its selectivity over methanol is increased. Simulations have indicated that water presence hinders DME production. Therefore, the removal of water is worth of further investigation and is likely to improve the process. The optimizations using the NSGA-II algorithm identified that a H-2/CO2 ratio of 5.0 yielded optimal conditions with high DME selectivity. At higher ratios, selectivity shifted towards MeOH, indicating increased separation costs. Lower temperatures favored MeOH production over DME.