Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor

Modeling diurnal and annual ethylene generation from solar-driven electrochemical CO2 reduction devices

“…Continued efforts to build upon this diurnal and annual model can accelerate the deployment of scaled solardriven CO 2 R pilot plants, which will be required to construct fully validated models of large-scale systems that wholly capture the transient influences of location-specific irradiance, temperature, and other environmental factors. Previous research into semi-empirical regression modeling for scaled alkaline 84 and PEM water electrolyzers, 85,86 and electrochemical CO 2 reduction, 34,87 highlights the need for the synergistic pairing of modeling and experimental results to inform each progressive point of scaling.…”

Smart manufacturing inspired approach to research, development, and scale-up of electrified chemical manufacturing systems

“…Models can also provide information about the current state of the system that cannot be sensed directly. Examples of how advanced modeling can be applied industrially include the prediction of catalyst lifetime or equipment failure, 71 adjusting for external factors such as changes in real-time feedstock, product and utility pricing, 72 or setting optimized system control set-points based on predicted performance. 73 , 74 , 75 Benefits of implementing SM in the industry have been demonstrated for a wide range of applications, 76 and industrial adoption has been successful for improving efficiency and safety in large scale industrial applications.…”

“…From this platform, data can be easily accessed in a centralized location and in a standardized format along with relevant sensor information, which is very important when building models of the reactor performance. This setup has been demonstrated in the real-time control of ethylene concentration in the RCE reactor effluent using proportional integral (PI) control 72 and multi-input-multi-output (MIMO) control of ethylene and CO concentrations. 89 …”

“…This approach was demonstrated by selecting cost-optimal set-points to conduct multivariable control experiments. 72 , 89 …”

“…Alternatively, the transient behavior of product concentrations in the effluent of the RCE cell can be approximated using a continuous stirred tank reactor (CSTR) approximation. 72 However, this type of approximation is not an accurate description of the real reactor and adds error to predictions. Thus, a model built only with electrochemical cell data can represent inherent reactor dynamics better than hybrid model approximations.…”