Development of a surrogate model of an amine scrubbing digital twin using machine learning methods

Advancements in the process industry require building more complex simulations and performing compu-tationally intensive operations like optimization. To overcome the numerical limit of conventional process simulations a surrogate model is a viable strategy. In this work, a surrogate model of an industrial amine scrubbing digital twin has been developed. The surrogate model has been built based on the process simulation created in Aspen HYSYS and validated as a digital twin against real process data collected during a steady-state operation. The surrogate relies on an accurate Design of Experiments procedure. In this case, the Latin-Hypercube method has been chosen and several nested domains have been defined in ranges around the nominal steady state operative condition. Several machine learning models have been trained using cross -validation, and the most accurate has been selected to predict each target. The resulting surrogate model showed a satisfactory performance, given the data available.

Automated summary

Advancements in the process industry require more complex simulations and computationally intensive operations. This study developed a surrogate model for an industrial amine scrubbing digital twin, based on a process simulation created in Aspen HYSYS and validated against real process data. The surrogate model relied on an accurate Design of Experiments procedure, using the Latin-Hypercube method and nested domains. Multiple machine learning models were trained and the most accurate one was selected. The resulting surrogate model showed satisfactory performance given the available data.