Genetic algorithm–artificial neural network model for the prediction of germanium recovery from zinc plant residues

Abstract

A multi-layer, feed-forward, back-propagation learning algorithm was used as an artificial neural network (ANN) tool to predict the extraction of germanium from zinc plant residues by sulphuric acid leaching. A genetic algorithm (GA) was used for the selection of training and testing data and a GA-ANN model of the germanium leaching system was created on the basis of the training data. Testing of the model yielded good error levels (r² = 0.95). The model was employed to predict the response of the system to different values of the factors that affect the recovery of germanium and the results facilitate selection of the experimental conditions in which the optimum recovery will be achieved.

References

Akkurt

Recovery of germanium and other metal values from the electrolyte purification precipitates of cinkur zinc plant residues. In Ozbayoglu

ed. Proc. IVth Int. Mineral Processing Symposium, Antalya, Turkey, October 1992 (Ankara: METU, 1992), 679–90.

Seifilluna

I. I.

Isolation of germanium tannate and gallate complexes by the flotation method. Zhurnal Prikladrwi Khimii, 39, 1973, 2077–9.

Cote

and Bauer

. Liquid-liquid extraction of germanium with oxine derivatives. Hydrometall., 5, 1980, 149–60.

Munakata

. Fundamentals of the new artificial intelligence: beyond traditional paradigms (New York: Springer-Verlag, 1998).

Hong-Guang

and Ji-Zong

. Prediction of compressive strength of concrete by neural networks. Cement and Concrete Research, 30, 2000, 1245-50.

Mohandes

M. A.

, Rehman

and Halawani

T. O

. A neural net-works approach for wind speed prediction. Renewable Energy, 13, no. 3, 1998, 345–54.

Task Committee

ASCE

. Artificial neural networks in hydrology, I: preliminary concepts. J. hydrologic Engng, 5 (2), 2000, 115–23.

Daskupta

. Evolving neuro controllers for a dynamic system using structured genetic algorithms. Applied Intelligence, 8, 1998, 113–21.

Padhy

N. P

. Unit commitment using hybrid models: a compara-tive study for dynamic programming, expert system, fuzzy system and genetic algorithms. Electrical Power and Energy Systems, 23, 2000, 827–36.

10.

Haykin

. Neural networks a comprehensive foundation (London: Macmillan, 1994).