PEMODELAN DAN PREDIKSI DENSITAS LARUTAN PORANG DAN XANTHAN GUM DENGAN MENGGUNAKAN MODEL-MODEL MACHINE LEARNING

Abstract

One physical characteristic that is helpful in comprehending the physical and chemical characteristics of a solution is the density of the polymer solution. Its primary function is to ascertain the polymer's concentration in solution. The density value can be used to estimate the polymer concentration in solution. The study of the flow and viscosity of polymer solutions also makes use of the interaction between the polymer and solvent. This study aims to establish a relationship between the density of porang and xanthan gum solutions and the percentage of porang, polymer content, and salinity. Machine learning models, like the Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), are used for modeling. The creation of these machine learning models used 471 digitized data of density curves of porang solution, xanthan gum solution, and porang-xanthan gum mixture solution. The training, validation, and testing processes of the ANN and ANFIS models provided average correlation coefficients of 0.99955 and 0.99999, respectively. Comparison between the estimates of the ANN and ANFIS models and the measurement results of 27 porang and xanthan gum solutions provided accurate results with correlation coefficients of 0.99893 and 0.99996, respectively.