March 3, 2026Open Access

Multi-Scale Digital Twin Framework with Physics-Informed Neural Networks for Real-Time Optimization and Predictive Control of Amine-Based Carbon Capture: Development, Experimental Validation, and Techno-Economic Assessment

Key Points

The framework achieves prediction errors below 1% for key variables such as CO2 loading and temperature, demonstrating high accuracy.
Validation against 500 test cases with CFD simulations confirms the model's reliability in predicting process performance.
A computational speedup of up to four orders of magnitude supports rapid response times under 100 ms for closed-loop control applications.
Sensitivity analysis highlights the liquid-to-gas ratio and MEA concentration as crucial parameters for enhancing mass transfer efficiency.

Abstract

Carbon capture and storage (CCS) is essential for achieving net-zero emissions, yet amine-based capture systems face significant challenges including high energy penalties (20–30% of power plant output) and operational costs (50–120/tonne CO2). This study develops and validates a novel multi-scale Digital Twin (DT) framework integrating Physics-Informed Neural Networks (PINNs) to address these challenges through real-time optimization. The framework combines molecular dynamics, process simulation, computational fluid dynamics, and deep learning to enable real-time predictive control. A key innovation is the sequential training algorithm with domain decomposition, specifically designed to handle the nonlinear transport equations governing CO2 absorption with enhanced convergence properties. The algorithm achieves prediction errors below 1% for key process variables (R2 > 0. 98) when validated against CFD simulations across 500 test cases. Experimental validation against pilot-scale absorber data (12 m packing, 30 wt% MEA) confirms good agreement with measured profiles, including temperature (RMSE = 1. 2 K), CO2 loading (RMSE = 0. 015 mol/mol), and capture efficiency (RMSE = 0. 6%). The trained surrogate enables computational speedups of up to four orders of magnitude, supporting real-time inference with response times below 100 ms suitable for closed-loop control. Under the conditions studied, the framework demonstrates reboiler duty reductions of 18. 5% and operational cost reductions of approximately 31%. Sensitivity analysis identifies liquid-to-gas ratio and MEA concentration as the most influential parameters, with mechanistic explanations linking these to mass transfer enhancement and reaction kinetics. Techno-economic assessment indicates favorable investment metrics, though results depend on site-specific factors. The framework architecture is designed for extensibility to alternative solvent systems, with future work planned for industrial-scale validation and uncertainty quantification through Bayesian approaches.

Mark Helpful

Bookmark

Relay

View Full Paper