JACIII Vol.20 No.2 pp. 231-237
doi: 10.20965/jaciii.2016.p0231


Intelligent Optimization of Cell Voltage for Energy Saving in Process of Electrolytic Aluminum

Chenhua Xu*, Le Wang*, Xiaofeng Lin*, Zhi Li*, and Xin Yu**

*School of Electrical Engineering, Guangxi University
Nanning 530003, China
**School of Computer, Electronics and Information, Guangxi University
Nanning 530003, China

November 10, 2015
December 10, 2015
Online released:
March 18, 2016
March 20, 2016
process of electrolytic aluminum, cell voltage, NNGA, BPNN, kernel principal component analysis (KPCA)

Based on the characteristic of cell voltage fluctuations in the process of electrolytic aluminum, a new method based on neural-network-genetic-algorithm (NNGA) for the optimization of cell voltage is proposed in this paper. First, the method of kernel principal component based on analysis of electrolytic aluminum process is used to determine the operating parameters. Second, in order to predict cell voltage in real time, back propagation neural network (BPNN) is used to establish the cell voltage prediction model. Third, the model of the optimization control of cell voltage is constructed, and then, genetic algorithm is used to optimize cell voltage and obtain corresponding operating conditions. Finally, the actual production data is used to perform experimental verification. The results show that the proposed method based on NNGA is effective. The process of electrolytic aluminum can operate under the optimal production conditions, and the goal of saving energy is achieved.

  1. [1]  E. S. Yin, “160KA center cutting Prebake Aluminum production technology and management,” Central South University Press, pp. 47-51, 2003.
  2. [2]  M. Wang and F. M. Tao, “300KA aluminum cell saving technology practice,” Mining and Metallurgy, Vol.18, No.3, pp. 62-63, 2009.
  3. [3]  C. A. Tong and H. C. Luo, “Low voltage aluminum electrolytic production management,” World Nonferrous Metals, Vol.1, pp. 72-73, 2014.
  4. [4]  W. F. Xiao, “The production of 200KA aluminum cell voltage swing causes and treatment,” Light metal, Vol.10, pp. 25-27, 2007.
  5. [5]  D. Shi, X. L. Zhao, and B. L. Gao, “Aluminum cell voltage between the composition and real-time measurement,” J. of Materials and Metallurgy, Vol.13, No.2, pp. 128-12, 2014.
  6. [6]  H. S. Li, P. Tuo, and S. Wang, “Experimental study of industrial aluminum cell anode assembly additives comply with phosphorus pig iron,” Light metal, Vol.4, pp. 31-32, 2011.
  7. [7]  J. Guo, W. H. Gui, and X. H. Wen, “Multi-objective optimization of electrolytic production process,” J. of Central South University (Natural Science), Vol.43. No.2, pp. 548-549, 2012.
  8. [8]  R. Sarker, M. Mohammadian, and X. Yao, “Evolutionzry Optimization,” Dordrecht: Kluwer Academic Publishers, 2003.
  9. [9]  J. Kyngas and J. Hkakarainne, “Predicting sunspot numbers with evolutionary optimized neural networks,” Proc. of the 2nd Nordic Workshop on Genetic Algorithms and their Applications, pp. 173-180, 1996.
  10. [10]  J. A. Freeman and D. M. Skapura, “Nerual Networks-Algorithms, Applications and Programming Techniques,” New York: Addison-Wesley Publishing, 1991.
  11. [11]  H. Takahashi, T. Agui, and H. Nagahshi, “Designing Adaptive Neural Network Architectures and Their Learning Parameters Using Genetic Algorithms,” D. W. Ruck (Ed.), Proc. Science of ANNII, Orlando, Florido, pp. 208-369, 1993.
  12. [12]  M. Gen and R. Cheng, “Genetic Algorithms and Engineering Optimization,” Toronto: John Wiley & Sons, Inc., 2000.
  13. [13]  D. S. Weile and E. Michielssen, “Genetic Algorithm Optimization Applied to Electromagnetics: A Review,” IEEE Trans. Antennas and Propagation, Vol.45, No.3, 1997.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Mar. 24, 2017