Hybrid Learning of Interval Type-2 Fuzzy Systems Based on Orthogonal Least Squares and Back Propagation for Manufacturing Applications

• Autorzy: Mendez G. , Hernandez A.
• Języki publikacji: EN

Abstrakty

EN

This paper presents a novel learning methodology based on the hybrid algorithm for interval type-2 (IT2) fuzzy logic systems (FLS). Since in the literature only back-propagation method has been proposed for tuning of both antecedent and consequent parameters of type-2 fuzzy logic systems, a hybrid learning algorithm has been developed. The hybrid method uses recursive orthogonal least-squares method for tuning of consequent parameters as well as the back-propagation method for tuning of antecedent parameters. The systems were tested for three types of inputs: a) interval singleton b) interval type-1 (T1) non-singleton, c) interval type-2 non-singleton. The experimental results of the application of the hybrid interval type-2 fuzzy logic systems for scale breaker entry temperature prediction in a real hot strip mill were carried out for three different types of coils. They proved the feasibility of the systems developed here for scale breaker entry temperature prediction. Comparison with type-1 fuzzy logic systems shows that the hybrid learning interval type-2 fuzzy logic systems improve performance in scale breaker entry temperature prediction under the tested condition.

Słowa kluczowe

EN

type-2 fuzzy inference systems; type-2 neuro-fuzzy systems; hybrid learning; uncertain rule-based fuzzy logic systems

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2008
• Tom: Vol. 2, No. 1
• Strony: 23--32
• Opis fizyczny: Bibliogr. 23 poz., rys.

Twórcy

autor

Mendez G.

autor

Hernandez A.

• Instituro Tecnologico de Nuevo Leon, Av. Eloy Cavazos #2001, CP 67170, Cd. Guadelupe, NL, Mexico,

Bibliografia

• [1] Mendel J.M., Uncertain Rule-Based fuzzy Logic Systems: Introduction and New Directions, Upper Saddle River NJ: Prentice-Hall, 2001.
• [2] Aguado A., Temas de Identificadón y Control Adaptable, La Habana 10200 Cuba, Instituto de Cibernetica, Matematicasy Ffsica, 2000, (In Spanish).
• [3] Mendez M., Cavazos A., Leduc L, Soto R., "Hot Strip Mili Temperature Prediction Using Hybrid Learning Interval Singleton Type-2 FLS". In: IASTED International Conference on Modeling and Simulation, Palm Springs CA, 2003, pp.380-385.
• [4] Mendez M., Cavazos A., Leduc L., Soto R., "Modelling of a Hot Strip Mill Temperature Using Hybrid Learning for Interval Type-1 and Type-2 Non-Singleton Type-2 FLS". In: IASTED International Conference on Artificial Intelligence and Applications, Benalmadena Spain, 2003,pp.529-533.
• [5] Jang J. S. R.7 Sun C. -T., Mizutani E., Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Upper Saddle River, NJ: Prentice-Hall, 1997.
• [6] Taylor B. N., Kuyatt C. E., Guidelines for Evaluating and Expressing the Uncertainty of NIST Measurement Results, NIST Technical Note 1297, aitherburg MD, September 1994.
• [7] Wang, X., "Fuzzy Systems are Universal Approximators". In: Proceedings of the IEEE Conf. on Fuzzy Systems, San Diego 1992, pp. 1163-1170.
• [8] Wang X., Fuzzy Systems as Nonlinear Mapping. A Course in Fuzzy Systems and Control, Upper Saddle River, NJ: Prentice Hall PTR, 1997, pp. 118-127.
• [9] Wang L. X., „Fuzzy Systems as Nonlinear Dynamic System Identifiers". In: Proceedings of the 31th IEEE Conference on Decision and Control, Tucson, Arizona, 1992, pp. 897-902.
• [10] Wang L. X., Mendel J.M., "Back-Propagation Fuzzy Systems as Nonlinear Dynamic System Identifiers". In: Proceedings of the IEEE Conf. On Fuzzy Systems, San Diego, CA, 1992, pp. 1409-1418.
• [11] Martinetz T., Protzel P., Gramchow O., Sorgel G., Neural Network Control for Rolling Mills, ELITE Foundation EUFIT94, Achen, Germany, 1994, pp. 147-152.
• [12] General Electric Models: Users reference, Roanaoke VA, vol. l, 1993.
• [13] Lee Y., Cho H. S., "Neural Network Approach to the Control of the Piąte Width in Hot Plate Mills", IEEE International Joint Conference on Neural Networks, vol. 5, Washington DC, 1999, pp. 3391-3396.
• [14] Ljung L., System Identification: Theory for the User, Prentice Hall Inc., Englewood Cliff NJ, 1987.
• [15] Fausett L., Fundamental of Neural Networks, Prentice Hall Inc., Englewood Cliff NJ, 1994.
• [16] Jang,S. R. J., Sun, C. -T., "Neuro-Fuzzy Modelling and Control". In: Proceedings of the IEEE, vol. 3, 1995, pp. 378-406.
• [17] Sato N„ Kamada N., Naito S„ Fukushima T., Fujino M., "Application of Fuzzy Control System to Hot Strip Mili". In: Proceedings of the IEEE International Conference on Industrial Electronics, Control, Instrumentation, San Diego CA, 1992, pp. 1202-06.
• [18] Bissessur Y., Martin E.B., Morris A.J., Kitson P., "Fault Detection in Hot Steel Rolling Using Neural Networks and Multivariate Statistics", IEE Proceedings Control Theory and Application, vol. 147,2000, pp. 633-640.
• [19] Watanabe L, Narazaki H., Kitamura A., Takahashi Y., Hasegawa H., "A New Mill-setup System for Hot Strip Rolling Mili that Integrates a Process Model and Expertise". IEEE International Conference on Computational Cybernetics and Simulation, vol 3, Orlando FL, 1997,pp.2818-2822.
• [20] Schalng M., Poppe T., "Neural Network for Steel Manu-facturing", IEEE Expert, vol. 11,1996, pp. 8-9.
• [21] Yao X., Tieu A.K., Fang X.D., Frances D., "Neural Network Application to Head & Tail Width Control in Hot Strip Mi U", IEEE International Conference on Neural Networks, vol 1. Orlando FL, 1995, pp. 433-437.
• [22] Kim Y.S., Yum B.J., Kim M., "Robust Design of Artificial Neural Network for Roll Force Prediction in Hot Strip Mill", IEEE International Joint Conference on Neural Network, vol. 4, Washington DC, 2001, pp. 2800-2804.
• [23] Liang Q., Mendel J. M., "Interval type-2 fuzzy logic systems: Theory and design, Trans. Fuzzy Systems, 2000,pp.535-550.