Parameter estimation of dynamic GMDH neural networks with the bounded-error technique

• Autorzy: Mrugalski M. , Witczak M.
• Języki publikacji: EN

Abstrakty

EN

This paper presents a new identification method based on ANNs (Artificial Neural Networks). In particular, a GMDH (Group Method of Data Handling) type neural network whose neurons have hyperbolic tangent activation junctions is considered. For such a network type. a new approach based on a bounded-error set estimation technique is employed to estimate the parameters of the ANN. The final part of this work contains an illustrative example regarding modeling the juice temperature at the outlet of an evaporator at the Lublin Sugar Factory S.A.

Słowa kluczowe

EN

artificial neural network; ANN; GMDH; group method of data handling; system identification; bounded-error approach

PL

sztuczna sieć neuronowa; ANN; GMDH; metoda grupowej obróbki danych; identyfikacja systemów

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2002
• Tom: Vol. 10, nr 1
• Strony: 77--90
• Opis fizyczny: Bibliogr. 17 poz.

Twórcy

autor

Mrugalski M.

• Institute of Control and Computation Engineering, University of Zielona Góra, Podgórna 50, 65-246 Zielona Góra, Poland

autor

Witczak M.

• Institute of Control and Computation Engineering, University of Zielona Góra, Podgórna 50, 65-246 Zielona Góra, Poland

Bibliografia

• [1] Angeline P.J.: Evolution Revolution: An introduction to the special track on genetic and evolutionary programing, IEEE Expert, 1995, pp.6-10.
• [2] Calado Korbicz J., Patan K., Patton R., Sa da Costa Soft Computing Approach tofault Diagnosis for Dynamic Systems, European Journal of Control. Special Issue: Fundamental Issues in Control, 2001, Vol. 7, issue 2-3, pp. 248-287.
• [3] Duch W., Korbicz J., Rutkowski L., Tadeusiewicz R. (Red.): Biocybernetyka i inżynieria biomedyczna 2000. Sieci neuronowe, Akademicka Oficyna Wydawnicza Exit, Warszawa, 2000, (in Polish).
• [4] Edelmayer, A.: Research of quantitative and qualitative FDI methods based on data from Lublin Sugar Factory, Spec. Session IFAC Symp. SAFEPROCESS'2000. Prepr. IFAC Symp.: Fault Detection, Supervision and Safety of Technical Processes: SAFEPROCESS'2000, 2000, Budapest, Hungary, pp. 331-358.
• [5] Farlow S. J.: Self-Organizing Methods in Modeling - GMDH Type Algorithms, Marcel Dekker. New York, 1984.
• [6] Hertz J., Krogh R., Palmer G.: Introduction to the neural computation, Addison-Wesley Publishing Company, Inc., 1991.
• [7] Howard M., Angelo D.: The GA-P: A Genetic Algorithm and Genetic Programming Hybrid, IEEE Expert, 1995, pp. 11-15.
• [8] Ivakhnenko A.G., Muller J.A.: Self-Organizing of Nets of Active Neurons, System Analysis Modelling Simulation, 1995, Vol.20, pp.93-106.
• [9] Koza J. R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection, MA: The MIT Press, Cambridge, 1992.
• [10] Ljung L.: System Identification: Theory for the User, Prentice-Hall, London, 1987.
• [11] Michalewicz Z.: Genetic Algorithms + Data Structures = Evolution Programs, Springer. Berlin, 1996.
• [12] Mrugalski M., Witczak M.: A bounded-error approach to-parameter estimation of neural networks, Proc. of 10-th Inter. Conf. System - Modelling - Control. Zakopane, Polska, 2001, Vol. 2, pp. 65-70.
• [13] Patan K.: Artificial Dynamic Neural Networks and Their Applications in Modelling of Industrial Processes, Warsaw University of Technology, Faculty of Mechatronics, Warsaw Academic Press, 2000, PhD.Disseration.
• [14] Ploix S., Adrot O., Ragot J.: Bounding approach to the diagnosis of uncertain static systems, Proc. of 4-th IFAC Symp. Fault Detection Supervision and Safety for Technical Processes SAFEPROCESS’2000. Budapest, Hungary, 2000, Vol. 2, pp. 149-154.
• [15] Schweppe F. G : Recursive state estimation: unknown but bounded errors and system inputs, IEEE Trans. Automatic Control, 1998, Vol. 13, pp. 22-29.
• [16] Uciński D.: Measurement Optimization for Parameter Estimation in Distributed Systems, Technical University Press, Zielona Góra, 1999.
• [17] Walter E., Pronzato L.: Identification of parametric models from experimental data, Springer. London, 1996.