A Machine Learning Method for State Identification of Superheat Degree with Flame Interference

  • Shiwei Zhao
  • Yongfang Xie
  • Weichao YueEmail author
  • Xiaofang Chen
Conference paper
Part of the The Minerals, Metals & Materials Series book series (MMMS)


The superheat degree in the process of aluminium electrolysis is an important indicator for judging the condition of the electrolysis cell. In the actual production process, the artificial observation of the fire hole is usually used for judgment and decision of cell condition. However, the decreasing number and frequent flow of experienced technicians make it difficult to guarantee the accuracy of this complex work. Although there exist some methods for state identification of superheat degree, they do not consider flame interference, resulting in decreasing of accuracy. In view of this fact, a method for state identification of superheat degree with flame interference is proposed, and the proposed method is compared with the existing method on 17 aluminium electrolysis cells. The vilification result shows that the proposed method has a better performance than the existing methods. Moreover, it reveals that the proposed method is feasible for identification with flame interference. In addition, it can provide suggestions for the technicians to judge the state of superheat degree.


Superheat degree Electrolysis cell Fire hole Flame interference Features extraction 



Supported by National Natural Science Foundation of China (61773405, 61533020, 61751312, 61725306, 61621062), the teachers-students co-innovation project of Central South University (502390003).


  1. 1.
    Yue W, Chen X, Gui W et al (2017) A knowledge reasoning fuzzy-bayesian network for root cause analysis of abnormal aluminum electrolysis cell condition. Front Chem Sci Eng 11(3):414–428CrossRefGoogle Scholar
  2. 2.
    Chen Z, Li Y, Chen X et al (2017) Semantic network based on intuitionistic fuzzy directed hyper-graphs and application to aluminum electrolysis cell condition identification. IEEE Access 5:20145–20156CrossRefGoogle Scholar
  3. 3.
    Shuiping Z, Fuwei C (2010) Dynamic decision model for amount of AlF3 addition in industrial aluminum electrolysis. In: Proceedings of the 8th world congress on intelligent control and automation, Jinan, China, 7–9, July, 2010Google Scholar
  4. 4.
    Yang J-S, Yu H, Chen X-F, Zou Z (2017) Soft measuring model of superheat degree in the aluminum electrolysis production. In: Chinese automation congress (CAC), Jinan, China, 20–22, Oct 2017Google Scholar
  5. 5.
    Liu Y, Xia S, Yu H, Wang G (2017) Prediction of aluminum electrolysis superheat based on relative density noise filtering random forest. In: Chinese automation congress (CAC), Jinan, China, 20–22, Oct 2017Google Scholar
  6. 6.
    Xiaofang C, Xiaowei Y, Keke H (2017) Identification of superheat of aluminum electrolytic cell based on computer vision and expert rule. In: Chinese automation congress (CAC), Jinan, China, 20–22, Oct 2017Google Scholar
  7. 7.
    Gui W, Yue W, Chen X et al (2018) Process industry knowledge automation and applications in aluminum reduction production process. Control Theory Control Appl 35(07):887–899Google Scholar
  8. 8.
    Huang, H, Ma, G, Zhuang Y (2008) Vehicle license plate location based on Harris corner detection. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), Beijing, China, Sept 28–Oct 4, 2008Google Scholar
  9. 9.
    Kenney CS, Zuliani, M, Manjunath BS (2005) An axiomatic approach to corner detection. In: IEEE computer society conference on computer vision and pattern recognition, San Diego, California, 20–26, June, 2005Google Scholar
  10. 10.
    Xia T, Jing XS, Zou WJ, SO Automation (2018) A moving object detection method based on pyramid LK optical flow under dynamic background. Navigation & Control Google Scholar
  11. 11.
    Smith AR (1978) Color Gamut Transform Paris. In: ACM-SIGGAPH’78 conference proceedings, pp 12–18Google Scholar
  12. 12.
    G Guo, H Wang, D Bell, Y Bi, K Greer.(2003) KNN model-based approach in classification. Lecture Notes in Computer ScienceGoogle Scholar
  13. 13.
    Zhang S, Li X, Zong M et al (2017) Learning k for kNN classification. Acm Trans Intell Syst Technol 8(3):43Google Scholar
  14. 14.
    Guo H, Li Y, Li Y, et al (2016) BPSO-Adaboost-KNN ensemble learning algorithm for multi-class imbalanced data classification. Eng Appli Artif Intell 49(C):176–193Google Scholar

Copyright information

© The Minerals, Metals & Materials Society 2019

Authors and Affiliations

  • Shiwei Zhao
    • 1
  • Yongfang Xie
    • 1
  • Weichao Yue
    • 1
    Email author
  • Xiaofang Chen
    • 1
  1. 1.School of Information Science and EngineeringCentral South UniversityChangshaChina

Personalised recommendations