Improving the Estimation Accuracy of Copper Oxide Leaching in an Ammonia–Ammonium System Using RSM and GA-BPNN
- 16 Downloads
In this study, a response surface methodology (RSM) model was used to analyze and optimize the factors affecting copper leaching efficiency in a copper oxide ammonia-ammonium (AA) system based on the parameters of AA concentration (ammonium hydroxide and ammonium bicarbonate matched with 1: 1), leaching time, grinding fineness, liquid-solid ratio, and temperature. The RSM analysis showed that five individual variables had a significant influence and that the interaction between AA concentration and leaching time had the most significant influence on leaching efficiency. In order to improve the estimation accuracy of the copper leaching efficiency, a model consisting of a genetic algorithm and a back propagation neural network (GA-BPNN) was used to optimize the operation index. A back propagation feed forward neural network with 3 layers (5–10–1) was applied to predict copper leaching efficiency. The genetic algorithm was applied to analyze the optimal leaching conditions. The results revealed that the GA-BPNN model outperformed the RSM model for predicting and optimizing copper oxide AA leaching. The optimization results of the GA-BPNN resulted in an R2 of 0.99827 and the highest predicted copper leaching efficiency of 79.49% was obtained under the conditions of an AA concentration of 4.78 mol/L, a leaching time of 157 min, a grinding fineness of 86.86% (–74 μm content account), a liquid-solid ratio of 2.87: 1, and a temperature of 313.17 K. A prediction and optimization method combining RSM and GA-BPNN, as used in this paper, can be further employed as a reliable and accurate method for ore leaching.
Keywordsresponse surface methodology genetic algorithm BP neural network modeling copper oxide ammonia-ammonium leaching
Unable to display preview. Download preview PDF.
- 4.Ma, J.Y., Liu, Y.Q., Hu, H.P., and Chen, Q.Y., J. Cent. South. Univ., 2012, vol. 43, no. 6, pp. 2059–2068.Google Scholar
- 5.Zhang, T.M., Fang, J.J., Jiang, T.G., and Mao, Y.B., Conserv. Util. Miner. Resour., 2014, no. 1, pp. 26–29 (in Chinese).Google Scholar
- 9.Govindaraju, R.S., J. Hydrol. Eng., 2015, vol. 5, no. 2, pp. 115–123.Google Scholar
- 15.Liang, N.H., Zhai, W.B., and Cao, X.S., J. Chin. Coal. Soc., 2008, vol. 33, no. 9, pp. 977–982.Google Scholar
- 16.Allahkarami, E., Nuri, O.S., Abdollahzadeh, A., Rezaiet, B., and Maghsoudi., B., Physicochem. Probl. Mi., 2017, vol. 53, no. 1, pp. 366–378.Google Scholar
- 17.Dučić, N., Ćojbašić, Ž., Slavković, R., Jordović, B., and Purenović, J., Hem. Ind., 2016, vol. 70, no. 6, pp. 1–32.Google Scholar