(2205-7386) Identification of cement rotary kiln using type 2 Takagi-Sugeno neuro-fuzzy system considering the effect of different noisy condition

Document Type : Research Paper

Authors

Electrical Engineering Department, K.N. Toosi University of Technology, Tehran, Iran

Abstract

A Cement rotary kiln is the main part of the cement production process, which has always attracted many researchers’ attention. However, this complex nonlinear system has not been modeled efficiently, which can make an appropriate performance, especially in noisy condition. In this work, the type 2 Takagi-Sugeno neuro-fuzzy system (T2TSNFS) is used to identify the cement rotary kiln, and the gradient descent (GD) algorithm is applied for tuning the parameters of antecedent and consequent parts of fuzzy rules. In addition, the optimal inputs of the system are selected by the genetic algorithm (GA) to achieve less complexity in the fuzzy system. The data relating to the Saveh White Cement (SWC) factory is used in the simulations. The Results demonstrate that the proposed identifier has an appropriate performance in noisy conditions. Furthermore, in this work, T2TSNFS is evaluated in noisy conditions, which had not been worked out before in related research works. Also, T2TSNFS and type 1 Takagi-Sugeno neuro-fuzzy system (T1TSNFS) are compared. The simulations show that T2TSNFS has more proper performance when the standard deviation of noise increases.

Keywords

References

[1] H. Aghdasinia, S. S. Hosseini, J. Hamedi, Improvement of a cement rotary kiln performance using arti cial neural network, Journal of Ambient Intelligence and Humanized Computing, 12 (2021), 7765-7776.
[2] M. Akalp, A. L. Dominguez, R. Longchamp, Supervisory fuzzy control of a rotary cement kiln, The Proceedings IEEE Electrotechnical Conference, 2 (1994), 754-757.
[3] A. Y. Alanis, E. N. Sanchez, A. G. Loukianov, E. A. Hernandex, Discrete-time recurrent high order neural networks for nonlinear identi cation, Journal of the Franklin Institute, 347(7) (2010), 1253-1265.
[4] P. V. Barr, J. K. Brimacombe, A. P. Watkinson, A heat transfer model for the rotary kiln: Part I, Pilot kiln trials, Metallurgical Transactions B, 20(B) (1989), 391-402.
[5] A. A. Boateng, P. V. Barr, A thermal model for the rotary kiln including heat transfer within the bed, International Journal of Heat and Mass Transfer, 39 (1996), 2131-2147.
[6] M. Z. Doghmane, M. Kidouch, S. Eladj, A. Ouali, Identi cation and modeling of a rotary kiln in cement plant based on ANN (MLP), Hatti, Arti cial Intelligence and Heuristics for Smart Energy Efficiency in Smart Cities. IC-AIRES. Lecture Notes in Networks and Systems, 361, Springer, Cham, 2021.
[7] M. Fallahpoor, A. Fatehi, B. N. Araabi, M. Azizi, Identi cation of cement rotary kiln using neural networks, First
Joint Congress on Fuzzy and Intelligent Systems Ferdowsi University of Mashhad, Iran, (2007), 29-31.
[8] M. Fallahpour, A. Fatehi, B. N. Araabi, M. Azizi, A neuro-fuzzy controller for rotary cement kilns, Proceedings of the 17th World Congress The International Federation of Automatic Control, Seoul, Korea, July 6-11, 2008.
[9] A. Fatemi Moghaddam, A. Shari , M. Teshnehlab, Prediction and identi cation of nonlinear rotary cement kiln system with neuro-fuzzy ANFIS network by using feature selection with genetic algorithm, Journal of Control, 5(2) (2011), 22-33.
[10] V. Hoenig, Evaluation of the energy performance of cement kilns in the context of co-processing (Technical Report), European Cement Research Academy GmbH (ecra), 2016, Available on: https://cembureau.eu/media/oyahklgk/12042-ecra-energy-performance-cement-kilns-2017-10-15.pdf.
[11] D. Karaboga Bagis, Evolutionary algorithm-based fuzzy PD control of spillway gates of dams, Journal of the Franklin Institute, 344(8) (2007), 1039-1055.
[12] C. C. Ku, P. H. Huang, W. J. Chang, Passive fuzzy controller design for nonlinear systems with multiplicative noises, Journal of the Franklin Institute, 347(5) (2010), 732-750.
[13] I. Makaremi, A. Fatehi, B. N. Araabi, Lipschitz numbers: A medium for delay estimation, Proceedings of the 17th IFAC World Congress, 2008.
[14] I. Makaremi, A. Fatehi, B. N. Araabi, Abnormal condition detection in cement rotary kiln with system identi cation methods, Elsevier Ltd. Journal of Process Control, 19 (2009), 1538-1545.
[15] M. A. Martins, L. S. Oliveira, A. S. Franca, Modeling and simulation of petroleum coke calcination in rotary kilns, Fuel, 80 (2001), 1611-1622.
[16] M. A. Martins, L. S. Oliveira, A. S. Franca, Modeling and simulation of limestone calcination in rotary kilns, ZKG International, 55(4) (2002), 76-87.
[17] E. Mastorakos, A. Massias, C. D. Tsakiroglou, D. A. Goussis, V. N. Burganos, CFD predictions for cement kiln including  ame modeling, heat transfer and clinker chemistry, Applied Mathematical Modeling, 23 (1999), 55-76.
[18] N. Moradkhani, M. Teshnehlab, Identi cation of cement rotary kiln in noisy condition using Takagi-Sugeno neuro-fuzzy system, Journal of AI and Data Mining, 7(3) (2019), 367-375.
[19] K. S. Mujumdar, V. V. Ranade, CFD simulations of heat transfer in transverse plane of rotating kilns, Chemcon, 2002.
[20] E. A. Muravyova, R. R. Mustaev, Development of an arti cial neural network for controlling motor speeds of belt weighers and separator in cement production, Optical Memory and Neural Networks, 26 (2018), 289-297.
[21] O. Nelles, Nonlinear system identi cation, Springer-Verlag, Berlin, 2001.
[22] M. Nie, W. W. Tan, Towards an efficient type-reduction method for intervaltype-2 fuzzy logic systems, IEEE International Conference on Fuzzy Systems, Hong Kong, 2008.
[23] G. Noshirvani, A. Fatehi, B. N. Araabi, M. Shirvani, M. Azizi, Comparison of rotary cement kiln identi ed models, Proceedings of the IEEE International Conference on Control and Automation, (2009), 1290-1295. 
[24] R. Noshirvani, M. Shirvani, A. Fatehi, Linear identi cation of white rotary cement kiln, ICINCO, Italy, 2009.
[25] M. Paul, K. S. Mujumdar, V. V. Ranade, Modeling of rotary cement kilns, Chemcon, 2002.
[26] M. L. Presti, R. Poluzzi, A. Zanaboni, Synthesis of fuzzy controller through neural networks, Fuzzy Sets and Systems, 71(1) (1996), 46-70.
[27] N. Qian, On the momentum term in gradient descent learning algorithms, Neural Networks, 12 (1999), 145-151.
[28] V. V. Ranade, K. S. Mujumdar, CFD simulations of solid motion in the transverse plane of rotating kilns, Proceedings of the third International Conference on CFD in the Minerals and Process Industries, 2003.
[29] M. Sadeghian, A. Fatehi, Identi cation of nonlinear predictor and simulator models of a cement rotary kiln by locally linear neuro-fuzzy technique, Proceedings of the Second International Conference on Computer and Electrical Engineering, (2009), 168-173.
[30] Z. Saghian, A. Esfahanipour, B. Karimi, A novel Kumaraswamy interval type-2 TSK fuzzy logic system for subway passenger demand prediction, Iranian Journal of Fuzzy Systems, 19(3) (2022), 69-87.
[31] A. Shari , M. Aliyari Shoorehdeli, M. Teshnehlab, Identi cation of cement rotary kiln using hierarchical wavelet fuzzy inference system, Journal of the Franklin Institute, 349 (2012), 162-183.
[32] H. A. Spang, A dynamic model of a cement kiln, Automatica, 8 (1972), 309-323.
[33] The NetlibWebsite, The bold driver network, 1994. Available on: http://www.netlib.org/utk/lsi/pcwLSI/text/node 226.html g3opt (accessed 12 October 2022).
[34] The Willamette University website, Momentum and Learning Rate Adaptation, 1999. Available on:
https://www.willamette.edu/ gorr/classes/cs449/momrate.html (accessed 12 October 2022).
[35] J. D. Williams, W. H. Woodall, J. B. Birch, J. H. Sullivan, Distribution of hotelling's T2 statistic based on the successive di erences estimator, Journal of Quality Technology, 38(3) (2006), 217-229.
[36] L. A. Zadeh, Fuzzy sets, Information and Control, 8 (1965), 338-353.
[37] L. A. Zadeh, A rationale for fuzzy control, World Scienti c Publishing Co. (1996), 123-126.
[38] T. Zhongda, L. Shujiang, W. Yanhong, W. Xiangdong, SVM predictive control for calcination zone temperature in lime rotary kiln with improved PSO algorithm, Transactions of the Institute of Measurement and Control, 40(10) (2018), 3134-3146. 
Iranian Journal of Fuzzy Systems
Volume 20, Issue 5
September and October 2023
Pages 33-45

Files

Share

How to cite

Statistics