Selectivity index and separation efficiency prediction in industrial magnetic separation process using a hybrid neural genetic algorithm

Abstract

It is essential to know the process efficiency in the industrial magnetic separation process under different operating conditions because it is required to control the process parameters to optimize the process efficiency. To our knowledge, there is no information about using artificial intelligence for modeling the magnetic separation process. Hence, finding a robust and more accurate estimation method for predicting the separation efficiency and selectivity index is still necessary. In this regard, a feed-forward neural network was developed to predict the separation efficiency and selectivity index. This model was trained to present a predictive model based on the percentage of iron, iron oxide and sulfur in mill feed and cobber feed, 80% passing size in mill feed and cobber feed and plant capacity. Therefore, this work aims to develop an intelligent technique based on an artificial neural network and a hybrid neural-genetic algorithm for modeling the concentration process. Results indicated that the values of mean square error and coefficient of determination for the testing phase were obtained 0.635 and 0.86 for selectivity index and of 4.646 and 0.84 for separation efficiency, respectively. In order to improve the performance of neural network, genetic algorithm was used to optimize the weights and biases of neural network. The results of modeling with GA-ANN technique indicated that the mean square error and coefficient of determination for the testing phase were achieved by 0.276 and 0.95 for selectivity index and of 1.782 and 0.92 for separation efficiency, respectively. The other statistical criteria for the GA-ANN model were better than those of the ANN model.

Predictive capability evaluation and mechanism of Ce (III) extraction using solvent extraction with Cyanex 572

“…However, this may lead to getting trapped in the local minima and slow down the convergence speed during the training phase. Therefore, to improve the efficiency of a neural network, the initial weights and the threshold of the network can be optimized using a genetic algorithm (GA) 28 . A genetic algorithm is a well-known technique for solving optimization problems 29 , 46 .…”

“…Therefore, statistical and artificial intelligence methods have been developed for monitoring purposes. These methods have been effectively applied in many processes 28 , 29 , especially in chemical engineering 30 . It has been proved that artificial intelligence methods outperform statistical techniques to predict process outputs 31 .…”

“…The use of artificial intelligence methods such as artificial neural network (ANN) 32 , support vector machine (SVM) 33 , and adaptive neural-based fuzzy inference system (ANFIS) 34 for modeling and simulation of chemical processes has attracted great attention in recent years. Among them, ANNs have been successfully applied in chemical processes such as flotation 28 , liquid–liquid extraction 35 , 36 , adsorption 32 , and so on 29 , 37 . Usually, the neural network training is done using random initial weights.…”

Arsenic Oxidation and Removal from Water via Core–Shell MnO2@La(OH)3 Nanocomposite Adsorption

“…The reference parameters were estimated via nonlinear regression by the Statistic 8.0 software (Statsoft, EUA, Tulsa, OK, USA). The coefficient of determination ( R 2 ), mean square error (MSE) and average relative error (ARE) were calculated to evaluate the goodness of fit [ 46 , 47 , 48 ]. The data were subjected to analysis of variance (ANOVA) using the General Linear Model and significance was declared with p < 0.05.…”