Development of a mathematical model for investigation of hollow-fiber membrane contactor for membrane distillation desalination

Abstract

This research investigates the predictive modeling of a dataset containing parameters denoted by r(m), z(m), and T(K) which is temperature. The considered process is a membrane distillation (MD) for separation of compounds based on temperature gradient. A membrane contactor is used for the process, and the computations are performed in the context of computational fluid dynamics (CFD) and machine learning. The dataset, which is generated by CFD modeling and encompasses over 5,000 data points, is analyzed using three distinct regression models: Support Vector Machine (SVM), Deep Neural Network (DNN), and Kernel Ridge Regression (KRR). Hyperparameter tuning is performed employing the Stochastic Fractal Search (SFS) algorithm. Our findings unraveled the nuanced intricacies of each model's performance, gauged through a comprehensive set of metrics. The RMSE, MAPE, and R2 score collectively offer a robust evaluation framework. The Deep Neural Network (DNN) exhibits a compelling RMSE of 7.7001E-01, a remarkably low MAPE of 2.05131E-03, and an impressive R2 score of 0.97054. Meanwhile, the Support Vector Machine (SVM) showcases a notable RMSE of 1.7215E-01, a minimal MAPE of 2.90820E-04, and a remarkably high R2 score of 0.99839. On the other hand, the Kernel Ridge Regression (KRR) model presents an RMSE of 1.3588E + 00, a MAPE of 2.63550E-03, and an R2 score of 0.90042.