Data-driven modeling and optimization of an industrial phosphoric acid production unit

Abstract

In this work, a supervised machine learning (ML) multi-output regression approach is investigated to build predictive models for an industrial unit of phosphoric acid production. More specifically, multioutput data-driven regression is applied to simultaneously estimate nine outputs (Reactor temperature, chemical yield (RC), P2O5 concentration in the phosphoric acid, and chemical losses in gypsum) under different operating conditions. The presented methods are linear regression and decision tree regression models. The use of decision tree regression provides high accuracy compared to linear regression. The decision tree model leads to a high value of the coefficient of determination (R2 = 0.994, on the testing set not used for the modeling), and to low values of the mean squared error (MSE) and mean absolute error (MAE). The best parameters of the decision tree provide higher fitness values than other depth levels. The optimal values in the training stage are 0.002, 0.007, and 0.994 for MSE, MAE, and R2, respectively. Applying decision tree regression can correctly model the data of the phosphoric acid manufacturing unit with satisfying fitness criterion and important conclusions on the process coherent with phenomenological models, as well as supplementary and novel insights.