Artificial neural network prediction of aluminum extraction from bauxite in the Bayer process

作者：Duric Isidora; Mihajlovic Ivan^*; Zivkovic Zivan; Keselj Dragana

来源：Journal of the Serbian Chemical Society, 2012, 77(9): 1259-1271.

DOI：10.2298/JSC110526193D

• leaching
• bauxite
• Bayer process
• statistical modeling
• neural networks

This paper presents the results of statistical modeling of the bauxite leaching process, as part of the Bayer technology for alumina production. Based on the data collected during the period 2008-2009 (659 days) from the industrial production in the Alumina Factory Birac, Zvornik (Bosnia and Herzegovina), the above-mentioned process was statistically modeled. The dependant variable, which was the main target of the modeling procedure, was the degree of Al2O3 recovery from boehmite bauxite during the leaching process. The statistical model was developed as an attempt to define the dependence of the degree of Al2O3 recovery on the input variables of the leaching process, i.e., the composition of the bauxite, the composition of the sodium aluminate solution and the caustic module of the solution before and after the leaching process. As statistical modeling tools, multiple linear regression analysis (MLRA) and artificial neural networks (ANNs) were used. The fitting level obtained using MLRA, was R-2 = 0.463, while the ANN resulted in an R-2 value of 0.723. In this way, the model defined using the ANN methodology could be used for the efficient prediction of the degree of recovery of Al2O3 as a function of the process inputs, under the industrial conditions of the Alumina Factory Birac, Zvornik. The proposed model also has a universal character and, as such, is applicable in other factories employing the Bayer technology for alumina production.

• 出版日期2012