Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Engineering >> 2019, Volume 5, Issue 6 doi: 10.1016/j.eng.2019.10.005

A Data and Knowledge Collaboration Strategy for Decision-Making on the Amount of Aluminum Fluoride Addition Based on Augmented Fuzzy Cognitive Maps

School of Information Science and Engineering, Central South University, Changsha 410083, China

Received:2018-10-13 Revised:2019-01-20 Accepted: 2019-02-14 Available online:2019-10-16

Next Previous


In the aluminum reduction process, aluminum fluoride (AlF3) is added to lower the liquidus temperature of the electrolyte and increase the electrolytic efficiency. Making the decision on the amount of AlF3 addition (referred to in this work as MDAAA) is a complex and knowledge-based task that must take into consideration a variety of interrelated functions; in practice, this decision-making step is performed manually. Due to technician subjectivity and the complexity of the aluminum reduction cell, it is difficult to guarantee the accuracy of MDAAA based on knowledge-driven or data-driven methods alone. Existing strategies for MDAAA have difficulty covering these complex causalities. In this work, a data and knowledge collaboration strategy for MDAAA based on augmented fuzzy cognitive maps (FCMs) is proposed. In the proposed strategy, the fuzzy rules are extracted by extended fuzzy k-means (EFKM) and fuzzy decision trees, which are used to amend the initial structure provided by experts. The state transition algorithm (STA) is introduced to detect weight matrices that lead the FCMs to desired steady states. This study then experimentally compares the proposed strategy with some existing research. The results of the comparison show that the speed of FCMs convergence into a stable region based on the STA using the proposed strategy is faster than when using the differential Hebbian learning (DHL), particle swarm optimization (PSO), or genetic algorithm (GA) strategies. In addition, the accuracy of MDAAA based on the proposed method is better than those based on other methods. Accordingly, this paper provides a feasible and effective strategy for MDAAA.


Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Fig. 14

Fig. 15

Fig. 16

Fig. 17


[1]  Yue W, Chen X, Gui W, Xie Y, Zhang H. A knowledge reasoning Fuzzy-Bayesian network for root cause analysis of abnormal aluminum electrolysis cell condition. Front Chem Sci Eng 2017;11(3):414–28. link1

[2]  Kvande H. Current efficiency of alumina reduction cells. In: Campbell PG, editor. Light metals 1989: Proceedings of the Technical Sessions by the TMS Light Metals Committee at the 118 TMS Annual Meeting; 1989 Feb 27–Mar 3; Las Vegas, NV, USA. Pittsburgh: The Minerals, Metals & Materials Society; 1989. p. 261–8. link1

[3]  Zeng S, Li J, Peng Q. Model predictive control of superheat for prebake aluminum production cells. In: DeYoung DH, editor. Light Metals 2008: Proceedings of the Technical Sessions Presented by the TMS Aluminum Committee at the TMS 2008 Annual Meeting & Exhibition; 2008 Mar 9–13; New Orleans, LA, USA. Pittsburgh: The Minerals, Metals & Materials Society; 2009. p. 347–50. link1

[4]  Desclaux P. AlF3 additions based on bath temperature measurements. In: Zabreznik R, editor. Light Metals 1987: Proceedings of the Technical Sessions Sponsored by the TMS Light Metal Committee at the 116th Annual Meeting; 1987 Feb 24–26; Denver, CO, USA. Pittsburgh: The Minerals, Metals & Materials Society; 1987. p. 309–13. link1

[5]  Guo J, Gui W, Wen X. Multi-objective optimization for aluminum electrolysis production process. J Cent South Univ 2012;43(2):548–53. link1

[6]  Kolås S. Defining and verifying the ‘‘correlation line” in aluminum electrolysis. JOM 2007;59(5):55–60. link1

[7]  Kloetstra K, Benninghoff S, Stam M, Toebes B. Optimisation of aluminium fluoride control at Aluminum Delfzijl. In: Proceedings of the 7th Australasian Aluminum Smelting Technology Conference and Workshop; 2001 Nov 11–16; Melbourne, VIC, Australia Sydney: Centre for Electrochemical and Minerals Processing. p. 506–14. link1

[8]  Dupuis M. Excess AlF3 concentration in bath control logic. In: Proceedings of National Conference on Advancements in Aluminum Electrolysis; 2006 Feb 11; Angul, India; 2006 p. 309–13. link1

[9]  Salt DJ. Bath chemistry control system. In: Bearne G, Dupuis M, Tarcy G, editors. Essential readings in light metals. Cham: Springer; 2016. p. 798–803. link1

[10]  Meghlaoui A, Al Farsi YA, Aljabri NH. Analytical and experimental study of fluoride evolution. In: Schneider WA, editor. Light Metals 2002: Proceedings of the Technical Sessions Presented by the TMS Aluminum Committee at the 131st TMS Annual Meeting; 2002 Feb 17–21; Seattle, WA, USA. Pittsburgh: The Minerals, Metals & Materials Society; 2002. p. 283–8. link1

[11]  Entner PM, Gudmundsson GA. Further development of the temperature model. In: Hale W, editor. Light Metals 1996: Proceedings of the Technical Sessions Presented by the TMS Light Metals Committee at the 125th TMS Annual Meeting; 1996 Feb 4–8; Anaheim, CA, USA. Pittsburgh: The Minerals, Metals & Materials Society; 1996. p. 445–9. link1

[12]  Zeng S, Cui F. Dynamic decision model for amount of AlF3 addition in industrial aluminum electrolysis. In: Proceedings of the 3rd International Conference on Mechatronics, Robotics and Automation; 2015 Apr 20–21; Shenzhen, China. Paris: Atlantis Press; 2015. p. 307–18. link1

[13]  Hyland MM, Patterson EC, Stevens-Mcfadden F, Welch BJ. Aluminium fluoride consumption and control in smelting cells. Scand J Metall 2001;30 (6):404–14. link1

[14]  Kolås S, Støre T. Bath temperature and AlF3 control of an aluminum electrolysis cell. Control Eng Pract 2009;17(9):1035–43. link1

[15]  Huang Y, Qu X, Zhou JM. Coupled heat/mass-balance model for analyzing correlation between excess AlF3 concentration and aluminum electrolyte temperature. Trans Nonferrous Met Soc China 2009;19(3):724–9. link1

[16]  Haupin W, Kvande H. Mathematical model of fluoride evolution from hallhéroult cells. In: Bearne G, Dupuis M, Tarcy G, editors. Essential readings in light metals. Cham: Springer; 2016. p. 903–9. link1

[17]  Drengstig T, Ljungquist D, Foss BA. On the AlF3 and temperature control of an aluminum electrolysis cell. IEEE Trans Contr Syst Technol 1998;6(2):157–71. link1

[18]  Wee YY, Cheah WP, Tan SC, Wee KK. A method for root cause analysis with a Bayesian belief network and fuzzy cognitive map. Expert Syst Appl 2015;42 (1):468–87. link1

[19]  Papageorgiou EI, Salmeron JL. A review of fuzzy cognitive maps research during the last decade. IEEE Trans Fuzzy Syst 2013;21(1):66–79. link1

[20]  Mls K, Cimler R, Vašcˇák J, Puheim M. Interactive evolutionary optimization of fuzzy cognitive maps. Neurocomputing 2017;232:58–68. link1

[21]  Nápoles G, Concepción L, Falcon R, Bello R, Vanhoof K. On the accuracyconvergence tradeoff in sigmoid fuzzy cognitive maps. IEEE Trans Fuzzy Syst 2018;26(4):2479–84. link1

[22]  Zdanowicz P, Petrovic D. New mechanisms for reasoning and impacts accumulation for rule-based fuzzy cognitive maps. IEEE Trans Fuzzy Syst 2018;26(2):543–55. link1

[23]  Kottas TL, Boutalis YS, Karlis AD. New maximum power point tracker for PV arrays using fuzzy controller in close cooperation with fuzzy cognitive networks. IEEE Trans Energ Convers 2006;21(3):793–803. link1

[24]  Baykasog˘lu A, Gölcük _ I. Development of a novel multiple-attribute decision making model via fuzzy cognitive maps and hierarchical fuzzy TOPSIS. Inf Sci 2015;301:75–98. link1

[25]  Zhang L, Chettupuzha AJA, Chen H, Wu X, AbouRizk SM. Fuzzy cognitive maps enabled root cause analysis in complex projects. Appl Soft Comput 2017;57:235–49. link1

[26]  Rezaee MJ, Yousefi S, Babaei M. Multi-stage cognitive map for failures assessment of production processes: an extension in structure and algorithm. Neurocomputing 2017;232:69–82. link1

[27]  Froelich W, Pedrycz W. Fuzzy cognitive maps in the modeling of granular time series. Knowl Base Syst 2017;115:110–22. link1

[28]  Obiedat M, Samarasinghe S. A novel semi-quantitative fuzzy cognitive map model for complex systems for addressing challenging participatory real life problems. Appl Soft Comput 2016;48:91–110. link1

[29]  Papageorgiou EI. Learning algorithms for fuzzy cognitive maps: a review study. IEEE Trans Syst Man Cybern C 2012;42(2):150–63. link1

[30]  Stach W, Kurgan L, Pedrycz W. Data-driven nonlinear Hebbian learning method for fuzzy cognitive maps. In: Proceedings of 2008 IEEE World Congress on Computational Intelligence; 2008 Jun 1–6; Hong Kong, China. New York: Institute of Electrical and Electronics Engineers; 2008. p. 1975–81. link1

[31]  Konar A, Chakraborty UK. Reasoning and unsupervised learning in a fuzzy cognitive map. Inf Sci 2005;170(2–4):419–41. link1

[32]  Froelich W, Salmeron JL. Evolutionary learning of fuzzy grey cognitive maps for the forecasting of multivariate, interval-valued time series. Int J Approx Reason 2014;55(6):1319–35. link1

[33]  Salmeron JL, Rahimi SA, Navali AM, Sadeghpour A. Medical diagnosis of rheumatoid arthritis using data driven PSO-FCM with scarce datasets. Neurocomputing 2017;232:104–12. link1

[34]  Luo X, Wei X, Zhang J. Guided game-based learning using fuzzy cognitive maps. IEEE Trans Learn Technol 2010;3(4):344–57. link1

[35]  Baykasoglu A, Durmusoglu ZDU, Kaplanoglu V. Training fuzzy cognitive maps via extended great deluge algorithm with applications. Comput Ind 2011;62 (2):187–95. link1

[36]  Christoforou AS, Andreou AS. A framework for static and dynamic analysis of multi-layer fuzzy cognitive maps. Neurocomputing 2017;232:133–45. link1

[37]  Mateou NH, Moiseos M, Andreou AS. Multi-objective evolutionary fuzzy cognitive maps for decision support. In: Proceedings of the IEEE Congress on Evolutionary Computation; 2005 Sep 2–4; Edinburgh, UK. New York: Institute of Electrical and Electronics Engineers; 2005. p. 824–30. link1

[38]  Stach W, Kurgan L, Pedrycz W, Reformat M. Genetic learning of fuzzy cognitive maps. Fuzzy Sets Syst 2005;153(3):371–401. link1

[39]  Papageorgiou EI, Stylios CD, Groumpos PP. Active Hebbian learning algorithm to train fuzzy cognitive maps. Int J Approx Reason 2004;37(3):219–49. link1

[40]  Zhou X, Yang C, Gui W. State transition algorithm. J Ind Manage Optim 2012;8 (4):1039–56. link1

[41]  Zhang F, Yang C, Zhou X, Gui W. Fractional-order PID controller tuning using continuous state transition algorithm. Neural Comput Appl 2018;29 (10):795–804. link1

[42]  Han J, Yang C, Zhou X, Gui W. A new multi-threshold image segmentation approach using state transition algorithm. Appl Math Model 2017;44:588–601. link1

[43]  Han J, Yang C, Zhou X, Gui W. Dynamic multi-objective optimization arising in iron precipitation of zinc hydrometallurgy. Hydrometallurgy 2017;173: 134–48. link1

[44]  Kulluk S, Özbakır L, Baykasog˘lu A. Fuzzy DIFACONN-miner: a novel approach for fuzzy rule extraction from neural networks. Expert Syst Appl 2013;40 (3):938–46. link1

[45]  Barakat N, Bradley AP. Rule extraction from support vector machines: a review. Neurocomputing 2010;74(1–3):178–90. link1

[46]  Yuan Y, Shaw MJ. Induction of fuzzy decision trees. Fuzzy Sets Syst 1995;69 (2):125–39. link1

[47]  Jain AK. Data clustering: 50 years beyond k-means. Pattern Recognit Lett 2010;31(8):651–66. link1

[48]  Dickerson JA, Kosko B. Virtual worlds as fuzzy cognitive maps. Presence (Camb) 1994;3(2):173–89. link1

[49]  Zeng SP, Li JH, Ren BJ. Fuzzy determination of AlF3 addition and aluminum tapping volume in aluminum electrolyzing process. Metall Ind Auto 2008;32 (1):18–21. link1

Related Research