Modelling a reverse water-gas shift reactor with an artificial neural network
Year: 2026
Type: article
Abstract: For process intensified Power-to-Liquid (PtL) systems, the reverse water-gas shift (rWGS) reaction is a key step to convert CO2 and H2 into CO-rich syngas. Conventional modelling approaches either provide thermodynamic limits or require detailed kinetic schemes that are costly to develop and still struggle to represent catalyst- and reactor-specific effects. In this work, a multi-output artificial neural network (ANN) is developed as a data-driven surrogate model for a tubular Ni/γ-Al2O₃ fixed-bed rWGS reactor. The network is trained on 396 experimentally determined operating points covering 550-950 °C, 1-8 bara, GHSV of 8 000-20 000 h-1 and H2:CO2 ratios between 2 and 3. The ANN predicts both CO2 conversion (XCO2) and CO selectivity (SCO) with an R² of 0.97 and test-set errors of MAE 1.9% and RMSE 3.3%. Compared to Gibbs-equilibrium calculations, the surrogate accurately reproduces experimentally observed deviations from equilibrium in the low- and mid-temperature regime and captures the stronger pressure sensitivity of SCO relative to XCO2. Explainable AI analysis using SHAP identifies temperature and H2:CO2 as dominant drivers, with pressure mainly steering methanation-driven selectivity losses and GHSV becoming relevant at low temperatures. The proposed framework provides an experimentally validated, interpretable tool for fast rWGS reactor screening and PtL process optimisation.
Source: Cleaner Chemical Engineering
Institution: Montanuniversität Leoben
Language: English
Subfield: Catalysis
Field: Chemical Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,270
OpenAlex ID: W7155186705