ANFIS based prediction of the aluminum extraction from boehmite bauxite in the Bayer process

Ivan Mihajlović,Isidora Đurić,Živan Živković

doi:10.2478/pjct-2014-0018

Abstract

Abstract This paper presents the results of nonlinear statistical modeling of the bauxite leaching process, as part of Bayer technology for alumina production. Based on the data, collected during the year 2011 from the industrial production in the alumina factory Birač, Zvornik (Bosnia and Herzegovina), nonlinear statistical modeling of the industrial process was performed. The model was developed as an attempt to define the dependence of the Al2O3 degree of recovery as a function of input parameters of the leaching process: content of Al2O3, SiO2 and Fe2O3 in the bauxite, as well as content of Na2Ocaustic and Al2O3 in the starting sodium aluminate solution. As the statistical modeling tool, Adaptive Network Based Fuzzy Inference System (ANFIS) was used. The model, defined by the ANFIS methodology, expressed a high fitting level and accordingly can be used for the efficient prediction of the Al2O3 degree of recovery, as a function of the process inputs under the industrial conditions.

Highlights

In 1888, Karl Josef Bayer developed and patented a process which has become the cornerstone of the aluminum production industry worldwide[1]
For the modeling of the bauxite leaching process, the data were collected by measuring the important input and output process parameters, defined in the previous text
The reason to use the Adaptive Network Based Fuzzy Inference System (ANFIS) for modeling the boehmite bauxite leaching process, presented in this paper, can be found in the previous research presented in manuscripts[1, 15, 16]

Summary

INTRODUCTION

In 1888, Karl Josef Bayer developed and patented a process which has become the cornerstone of the aluminum production industry worldwide[1]. Bayer process includes the high pressure leaching of bauxites in a concentrated sodium hydroxide (caustic) solution at temperatures, ranging from 373 K (100oC) to 523 K (250oC), depending on the mineralogical form of aluminum hydroxide in the bauxite[6,7,8,9]. Being influenced by large number of different input parameters, the process of bauxite leaching, under industrial conditions of Bayer technology for alumina production, is highly complex. Based on the facts described in previous sections, the main objective pursued in this work was to create a mathematical model for the prediction of the degree of Al2O3 recovery (output of the process), during boehmite bauxite leaching, as the function of the input parameters of the process. The obtained model presents a great advantage due to its ability to predict accurately enough the output of the investigated process, and as such is of great practical importance

EXPERIMENTAL DATA

RESULTS AND DISCUSSION

ADAPTIVE NETWORK BASED FUZZY INFERENCE SYSTEM

CONCLUSIONS

LITERATURE CITED