Data-driven surrogate modelling and multi-variable optimization of trickle bed and packed bubble column reactors for CO2 capture via enhanced weathering

作者：Lei Xing, Hai Jiang, Shuo Wang, Valerie J. Pinfield, Jin Xuan · 发表于：Chemical Engineering Journal · 年份：2022 · DOI：10.1016/j.cej.2022.139997 · 被引用次数：22 · 研究领域：Carbon Dioxide Capture Technologies、CO2 Sequestration and Geologic Interactions、Chemical Looping and Thermochemical Processes

Enhanced weathering (EW) of minerals could potentially absorb atmospheric CO 2 at gigaton scale per year and store it as bicarbonate and carbonate in the ocean. However, this process must be accelerated by engineered reactors, in which optimal reaction conditions maximise the CO 2 capture rate and minimise the energy and water consumption. In this work, trickle beds (TBs) and packed bubble columns (PBCs), operated with fresh water and CO 2 -rich flue gas, are chosen as typical chemical reactors to perform the EW-based CO 2 capture. We firstly develop experimentally validated physics-based mechanistic models then generate data to train data-driven surrogate models to achieve rapid prediction of performance and multi-variable optimization. Two surrogate models, namely, response surface methodology (RSM) and extended adaptive hybrid functions (E-AHF), are developed and compared, in which the effect of five design variables on three objective functions are investigated. Results show that the R 2 for the prediction of CO 2 capture rate (CR) and water consumption (WC) through RSM and E-AHF is higher than 0.84. For TB reactors, in particular, the calculated R 2 is higher than 0.96. The prediction accuracy of energy consumption (EC) through the RSM approach is, however, relatively poor (R 2 ∼ 0.79), but is improved by using the E-AHF surrogate model, increasing to R 2 ∼ 0.89. The developed data-driven surrogate model can rapidly predict the performance indicators of TB and PBC reacto...