Machine learning modeling of the volumetric overall mass transfer coefficient in a novel L-shaped pulsed sieve plate extraction column
Year: 2026
Type: article
Abstract: The volumetric overall mass transfer coefficient (K oc a) is a key design parameter in liquid-liquid extraction columns, yet reliable prediction remains difficult for non-standard geometries. This study applied machine learning to predict to predict K oc a in an L-shaped pulsed sieve plate extraction column using ANN, RF, and SVR models trained on experimental data from two liquid-liquid systems. The ANN model achieved the highest accuracy, with a test R² value above 0.98 and AARE below 6%, substantially outperforming published empirical correlations. Sensitivity analysis identified dispersed phase holdup and drop size as dominant variables. ANN-based response surface analysis identified optimal operating conditions, with residual diagnostics confirming the absence of systematic bias across the full range of predicted values.
Source: Scientific Reports
Authors: Vahid Rafiei, Sadegh Moradi
Institution: Arak University
Language: English
Topic: Fluid Dynamics and Mixing
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7202299670