Estimation of xanthate decomposition percentage as a function of pH, temperature and time by least squares regression and adaptive neuro-fuzzy inference system

Abstract

Estimating the xanthate decomposition percentage has a crucial role in the treatment of xanthate contaminated wastewaters and in the improvement of the flotation process performance. In this research, the modeling of xanthate decomposition percentage was performed using the least squares regression method and the Adaptive Neuro-Fuzzy Inference System (ANFIS). A multi-variable regression equation and the ANFIS models with various types and numbers of membership functions (MFs) were constructed, trained, and tested for the estimation of xanthate decomposition percentage. The statistical indices such as Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R2 ) were used to evaluate the performance of various models. The lowest values of RMSE and MAPE and the closest value of R2 to unity were determined for the ANFIS model with the triangular membership function and the number of input MFs 9 9 9 (0.766906, 3.553509 and 0.998793). This indicates that ANFIS is a powerful method in the estimation of xanthate decomposition percentage. The performance of new-adopted ANFIS data modeling was significantly better than the conventional least squares regression method.