Development of new correlation for the prediction of power number for closed clearance impellers using machine learning methods trained on literature data

Abstract

The accurate estimation of the power number for closed clearance impellers holds significant importance in industries such as chemical, biochemical, paper and pulp, as well as paints, pigments, and polymers. Existing state-of-the-art correlations for predicting power numbers, however, are inaccurate for impeller Reynolds number $\left(R{e}_I\right)>100$. In this study, we compiled a dataset of 1470 data points from 15 research articles in the open literature, covering five types of impellers: (i) anchor; (ii) gate; (iii) single helical ribbon; (iv) double helical ribbon; and (v) helical ribbon with screw. Six machine learning models, namely artificial neural networks (ANN), CatBoost regressor, extra tree regressor, support vector regressor, random forest, and XGBoost regressor, were developed and compared. The results revealed that ANN emerged as the most efficient model, demonstrating the highest testing R² value of 0.99 and the lowest testing MAPE of 7.3%. Further, we used the ANN model to develop a novel set of process correlations to estimate impeller power numbers for the industrially important anchor and double helical ribbon impellers: which significantly outperform the existing state-of-the-art correlations available in literature.