Advertisement

A Novel Prediction Model of Integrate Energy Consumption Per Ton Crude Steel Using Gene Expression Programming

  • Li-ping Zhang
  • Qiu-hua Tang
  • C. A. Floudas
  • Yong-nian Mao
  • Cai-fu Zheng
Conference paper

Abstract

The iron and steel industry is a fundamental part of national economy, but it is also the large energy user. The accurate predictability of the energy consumption is beneficial to seize the energy development trends and reduce the energy waste. According to the historical data of integrate energy consumption per ton crude steel (IECPTCS) about our country, a novel prediction model of the IECPTCS is proposed by using Gene expression programming (GEP). Firstly, the IECPTCS is divided into equal time intervals. The functional expression is represented by some symbols. A parameter, which is stored as constant, is defined in the terminal set. Secondly, the prediction model is obtained by genetic operation, which contains selection operation, mutation operation, recombination operation, transposition operation, etc. Finally, the experimental results show that the average error between the predicted value and the real value is 0.649 via GEP, which is superior to other approaches. It also illustrates that the novel prediction model can forecast the development trends of the IECPTCS accurately.

Keywords

Gene expression programming Prediction model Integrate energy consumption per ton crude steel 

Notes

Acknowledgment

This research is supported by the National Natural Science Foundation of China under Grant No. 51305311 and 51275366, and China Postdoctoral Science Foundation 2013M542073.

References

  1. 1.
  2. 2.
    A. Xie, Z. Lu. Analysis and forecast for integrate energy consumption per ton crude steel by grey system[J]. Iron and Steel. 1997, vol 32: 40-42.Google Scholar
  3. 3.
    M. Jin, X. Han, X. Chen. Application of the linear regression model in the analysis of the comprehensive energy consumption of Ton-steel[J]. Science & Technology of Baotou Steel (Group) Corporation. 2009, 35(1): 88-90.Google Scholar
  4. 4.
    G. Chen, W. Liu. Application of generalized regression neural network in BF iron-making energy intensity prediction. Energy for metallurgical industry. 2013, vol. 32, no. 4, pp. 15-18.Google Scholar
  5. 5.
    C. Ferreira. Gene expression programming: A new adaptive algorithm for solving problems. Complex Systems. 2001, vol. 13, no. 2, pp. 87–129.Google Scholar
  6. 6.
    Y. Yang, X. Li, L. Gao, X. Shao. Modeling and impact factors analyzing of energy consumption in CNC face milling using GRASP gene expression programming. The International Journal of Advanced Manufacturing Technology. online.Google Scholar
  7. 7.
    G .Wang, H. Bai, D. Cang, Y. Zhang, Y. Zong. Mathematical model for diagnosis of energy consumption bottlenecks in steel plants and its application. Journal of University of Science and Technology Beijing. 2009, vol. 31, no. 9, pp. 1195-1199.Google Scholar
  8. 8.
    T. Cai, W. Sun. Systems energy conservation and scientific energy utilization of iron and steel industry in China. Iron and Steel. 2012, vol. 47, no. 5, pp 1-8.Google Scholar
  9. 9.
    L. Nie, L. Gao, P. Li, X. Li. A GEP-based reactive scheduling policies constructing approach for dynamic flexible job shop scheduling problem with job release dates. The international journal of advanced technology. 2013 vol. 24, pp.763-774.Google Scholar
  10. 10.
    China Iron and Steel Industry Association. http://www.chinaisa.org.cn. 2015.

Copyright information

© Atlantis Press and the author(s) 2016

Authors and Affiliations

  • Li-ping Zhang
    • 1
  • Qiu-hua Tang
    • 1
  • C. A. Floudas
    • 2
  • Yong-nian Mao
    • 1
  • Cai-fu Zheng
    • 1
  1. 1.College of Machinery and AutomationWuhan University of Science and TechnologyWuhanChina
  2. 2.Texas A&M Energy InstituteTexas A&M UniversityCollege StationUSA

Personalised recommendations