A knowledge reasoning Fuzzy-Bayesian network for root cause analysis of abnormal aluminum electrolysis cell condition

Abstract

Root cause analysis (RCA) of abnormal aluminum electrolysis cell condition has long been a challenging industrial issue due to its inherent complexity in analyzing based on multi-source knowledge. In addition, accurate RCA of abnormal aluminum electrolysis cell condition is the precondition of improving current efficiency. RCA of abnormal condition is a complex work of multi-source knowledge fusion, which is difficult to ensure the RCA accuracy of abnormal cell condition because of dwindling and frequent flow of experienced technicians. In view of this, a method based on Fuzzy-Bayesian network to construct multi-source knowledge solidification reasoning model is proposed. The method can effectively fuse and solidify the knowledge, which is used to analyze the cause of abnormal condition by technicians providing a clear and intuitive framework to this complex task, and also achieve the result of root cause automatically. The proposed method was verified under 20 sets of abnormal cell conditions, and implements root cause analysis by finding the abnormal state of root node, which has a maximum posterior probability by Bayesian diagnosis reasoning. The accuracy of the test results is up to 95%, which shows that the knowledge reasoning feasibility for RCA of aluminum electrolysis cell.

Key words： abnormal aluminum electrolysis cell condition; Fuzzy-Bayesian network; multi-source knowledge solidification and reasoning; root cause analysis

Acknowledgements

The paper is supported by the National Natural Science Foundation of China (Grant Nos. 61533020 and 61374156). The authors would like to thank Prof. Zou Zhong, Central South University, and the experts of Zhengzhou Faxiang Aluminum Industry Co., LTD for providing data and information of aluminum electrolysis cell.Electronic Supplementary MaterialƒSupplementary material is available in the online version of this article at http://dx.doi.org/10.1007/s11705-017-1663-x and is accessible for authorized users.

References

1 Qiu Z X. Principles and Applications of Aluminum Electrolysis. Xuzhou: China University of Mining Press, 1998, 508–510

2 Gui W H, Wang  C, Xie Y F ,  Song S, Meng  Q F. Knowledge automation is a necessary method for universities to realize spanning development for process industry. China science founding, 2015(5): 337–342

3 Guo J, Gui  W H, Wen  X F. Multi-objective optimization for aluminum electrolysis production process. Journal of Central South University, 2012, 43(2): 548–553

4 Stam M A, Taylor  M P, Chen  J J J, Mulder  A, Rodrigo R . Common behaviour and abnormalities in aluminum reduction cells. TMS Light Metals,2008, 309–314

5 Majid N A A ,  Taylor M P ,  Chen J J J ,  Stam M A ,  Mulder A ,  Young B R . Aluminum process fault detection by multiway principal component analysis. Control Engineering Practice, 2011, 19(4): 367–379

6 Rooney J J, Heuvel  L N V. Root cause analysis for beginners. Quality progress, 2004, 37(7): 45–56

7 Doggett A M. Root cause analysis: A framework for tool selection. Quality Management Journal, 2005, 12(4): 34

8 Demirli K, Vijayakumar  S. Fuzzy assignable cause diagnosis of control chart patterns. Fuzzy Information Processing Society, 2008, 1–6

9 Ruiz-Sarmiento J R ,  Galindo C ,  Gonzalez-Jimenez J . Scene object recognition for mobile robots through semantic knowledge and probabilistic graphical models. Expert Systems with Applications, 2015, 42(22): 8805–8816

10 Kordy B, Pouly  M, Schweitzer P . Probabilistic reasoning with graphical security models. Information Sciences, 2016, 342: 111–131

11 Wee Y Y, Cheah  W P, Tan  S C, Wee  K K. A method for root cause analysis with a Bayesian belief network and fuzzy cognitive map. Expert Systems with Applications, 2015, 42(1): 468–487

12 Alaeddini A, Dogan  I. Using Bayesian networks for root cause analysis in statistical process control. Expert Systems with Applications, 2011, 38(9): 11230–11243

13 Weidl G, Madsen  A L, Israelson  S. Applications of object-oriented Bayesian networks for condition monitoring, root cause analysis and decision support on operation of complex continuous processes. Computers & Chemical Engineering, 2005, 29(9): 1996–2009

14 Ferreira L, Borenstein  D. A fuzzy-Bayesian model for supplier selection. Expert Systems with Applications, 2012, 39(9): 7834–7844

15 Cai B, Liu  Y, Fan Q ,  Zhang Y ,  Liu S Y ,  Ji R. Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network. Applied Energy, 2014, 114: 1–9

16 Zeng S P, Li  J, Ding L . Fault diagnosis system for 350 KA pre-baked aluminum reduction cell based on BP neural network. TMS–Light Metals, 2007

17 Taylor M P, Zhang  W D, Wills  V, Schmid S . A dynamic model for the energy balance of an electrolysis cell. Chemical Engineering Research & Design, 1996, 74(8): 913–933

18 Zhou T.Study of alumina concentration control based on intelligent characteristic model. Advanced Materials Research. Trans Tech Publications, 2011, 317: 1314–1317

19 Tessier J, Tarcy  G P, Batista  E, Wang X . Towards on-line monitoring of alumina properties at a pot level. Light Metals, 2012: 633–638

20 Zeng S P, Wang  S, Qu Y . Control of temperature and aluminum fluoride concentration based on model prediction in aluminum electrolysis. Advances in Materials Science and Engineering, 2014, 3:1–5

21 Kolås S, Støre  T. Bath temperature and AlF₃ control of an aluminum electrolysis cell. Control Engineering Practice, 2009, 17(9): 1035–1043

22 Ayyub B M, Klir  G J. Uncertainty modeling and analysis in engineering and the sciences. CRC Press, 2006, 3–7

23 Hancock J M. Bayesian network (belief network, causal network, knowledge map, probabilistic network). Dictionary of Bioinformatics and Computational Biology, 2004, 5–10

24 Pearl J. Fusion, propagation, and structuring in belief networks. Artificial Intelligence, 1986, 29(3): 241–288

25 Bishop C M. Pattern Recognition and  Machine Learning. New York: Springer-Verlag,2006, 373–375

26 Kabak M, Burmaoğlu  S, Kazançoğlu  Y. A fuzzy hybrid MCDM approach for professional selection. Expert Systems with Applications, 2012, 39(3): 3516–3525

27 Wan S. Power average operators of trapezoidal intuitionistic fuzzy numbers and application to multi-attribute group decision making. Applied Mathematical Modelling, 2013, 37(6): 4112–4126

28 Li P, Chen  G, Dai L ,  Zhang L . A fuzzy Bayesian network approach to improve the quantification of organizational influences in HRA frameworks. Safety Science, 2012, 50(7): 1569–1583

29 Dubois D, Prade  H. Operations on fuzzy numbers. International Journal of Systems Science, 1978, 9(6): 613–626

30 Hsu Y L, Lee  C H, Kreng  V B. The application of fuzzy Delphi method and fuzzy AHP in lubricant regenerative technology selection. Expert Systems with Applications, 2010, 37(1): 419–425