Abstract
Anthropogenic carbon-dioxide emissions, exceeding 51 billion tons annually, are a major driver of global climate impacts. Aqueous amine scrubbing offers an effective carbon-capture solution, but the energy-intensive thermal regeneration step of the process significantly increases costs, limiting large-scale adoption. To address these challenges, computational optimization of process and molecular design is promising but often too resource-intensive, emphasizing the need for efficient surrogate models. Specifically, we develop a surrogate model based on an artificial neural network (ANN) that is employed to replace rigorous phase-equilibrium computations performed with the SAFT-? Mie group contribution method within a steady-state aqueous amine carbon-capture process model. Our ANN is trained on 32,768 vapour–liquid equilibrium data points of a quaternary mixture of water, monoethanolamine, carbon dioxide, and nitrogen over industrially relevant temperature, pressure, and composition ranges, achieving mean-relative errors below 2% for most variables. The ANN is integrated into a computer aided process design (CAPD) framework and evaluated via mathematical optimization, with the total annualized cost (TAC) as the objective function. Compared to the rigorous process model, the model with the ANN surrogate exhibits reduced computational times of up to 81% while converging to near-identical optima within 1% of the TAC. With a robustness analysis across the lean-loading and desorber-pressure design space we show that the ANN effectively captures 90% of the investigated design space, vs. 77% for the rigorous model. In a multi-start optimization ensuring global optimality, the surrogate converges to the same point as the rigorous model, taking 10 h less. This demonstrates that carefully trained surrogate models can significantly accelerate process optimization and enable larger-scale applications, paving the way for future solvent and process co-design efforts.