A hybrid neural network/genetic algorithm to predict Zn(II) removal by ion flotation. Issue 6 (12th April 2020)

• Record Type: Journal Article
• Authors: Hoseinian, Fatemeh Sadat; Rezai, Bahram; Kowsari, Elaheh; Safari, Mehdi
• Is Part Of: Separation science and technology. Volume 55:Issue 6(2020)
• Page Start: 1197
• Page End: 1206
• Publication Date: 2020-04-12
• Subjects: Prediction -- Zn(II) flotation -- modelling -- hybrid neural-genetic algorithm -- sensitivity analysis; Separation (Technology) -- Periodicals; 660.284205
• DOI: 10.1080/01496395.2019.1582543
• Languages: English
• ISSNs: 0149-6395

Abstract

ABSTRACT: There are few methods to predict ion removal using ion flotation without lengthy experiments. The objective of this study was to model the Zn(II) flotation using a hybrid neural network/genetic algorithm (GANN) and multivariate linear regression (MLR). Mean square error and correlation coefficient values of 0.9228 and 190.1, respectively, for testing the datasets of the GANN model reveal the superiority of the GANN model in predicting the Zn(II) removal, while these values were obtained as 0.9125 and 220.36, respectively, for the MLR model. The results showed that this model could be useful in predicting the Zn(II) removal in response to changes in the input parameters.