Metrika članka

  • citati u SCindeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[=>]
  • posete u poslednjih 30 dana:0
  • preuzimanja u poslednjih 30 dana:0
članak: 1 od 1  
Tehnika
2013, vol. 68, br. 3, str. 473-479
jezik rada: srpski
vrsta rada: izvorni naučni članak

Primena NARX neuronske mreže za simulaciju rada sistema magnetne levitacije
Univerzitet u Nišu, Elektronski fakultet

Projekat

Istraživanje klimatskih promena i njihovog uticaja na životnu sredinu - praćenje uticaja, adaptacija i ublažavanje (MPNTR - 43007)
Razvoj novih informaciono-komunikacionih tehnologija, korišćenjem naprednih matematičkih metoda, sa primenama u medicini, telekomunikacijama, energetici, zaštititi nacionalne baštine i obrazovanju (MPNTR - 44006)
Istraživanje i razvoj nove generacije vetrogeneratora visoke energetske efikasnosti (MPNTR - 35005)

Sažetak

U ovom radu predstavljen je jedan način realizacije nelinearne autoregresivne neuronske mreže za potrebe simuliranja rada sistema magnetne levitacije. Najpre je model ovog visoko nelinearnog sistema detaljno opisan a nakon toga je opisan i NARX model neuronske mreže. Takođe su u radu opisane numeričke optimizacione tehnike za poboljšano treniranje mreže i dati su eksperimentalni rezultati rada treniranih NARX neuronskih mreža. Ovi rezultati potvrđuju da NARX neuronska mreža može uspešno da oponaša rad ovog nelinearnog sistema. Dobijeni model je pogodan prilikom projektovanja raznih upravljačkih algoritama.

Ključne reči

neuronska mreža; magnetni levitator; nelinearni model

Reference

Ahmad, I., Akramjavaid, M. (2010) Nonlinear model and controller design for magnetic levitation system. u: Signal Processing, Robotics and Automation, 9th International Conference, University of Cambridge, United Kingdom, February 20.-22., 324-328
Beale, M.H., Hagan, M.T., Demuth, H.B. (2012) Neural network toolbox 7: User’s guide
Broyden, C. (1972) Quasi-Newton methods. u: Murray W. [ur.] Numerical Methods for Unconstrained Minimization, New York: Academic Press, 87-106
David, R.C., Dragos, C.A., Bulzan, R.G., Precup, R.E., Petriu, E.M., Radac, M.B. (2012) Approach to Fuzzy Modeling of Magnetic Levitation Systems. International Journal of Artificial Intelligence, 9: A12-18
Dolga, V., Dolga, L. (2007) Modeling and simulation of a magnetic levitation system. Fascicle of Management and Technological Engineering, 1118-1124
Drago, C.A., Preitl, S., Precup, R.E., Bulzan, R.G., Petriu, E.M., Tar, J.K. (2010) Experiments in fuzzy control of a magnetic levitation system laboratory equipment. u: 8th International Symposium on Intelligent Systems and Informatics, Subotica, Serbia, 601-606
Drago, C.A., Preitl, S., Precup, R.E., Petriu, E.M. (2010) Magnetic levitation system laboratory-based education in control engineering. u: 3rd International Conference on Human System Interaction, Rzeszow, Poland, 496-501
Dragos, C.A., Precup, R.E., Petriu, E.M., Tomescu, M.L., Preitl, S., David, R.C., Radac, M.B. 2-DOF PI-fuzzy controllers for a magnetic levitation system. u: 8th International Conference on Informatics in Control, Automation and Robotics, Noordwijkerhout, Netherlands, vol. 1, 111-116
Inteco (2011) The magnetic levitation system (MLS): Users manual. http://www.inteco.com.pl
Lairi, M., Bloch, G. (1999) A neural network with minimal structure for maglev system modeling and control. u: IEEE International Symposium Intelligent Control/Intelligent Systems and Semiotics, Cambridge, MA, September, 15.-17. 1999, 40-45
Nawi, N.M., Ransing, R.S., Ransing, M.R. (2007) An improved conjugate gradient based learning algorithm for back propagation neural networks. International Journal of Computational Intelligence, 780-789
Pedersen, G.K.M., Yang, Z. (2006) Multi-objective PID-controller tuning for a magnetic levitation system using NSGA-II. u: 8th Annual Conference on Genetic and Evolutionary Computation, July, 8.-12. 2006, Seattle, Washington, USA, 1737-1744
Ranganathan, A. (2004) The Levenberg-Marquardt algorithm: Tutorial on LM Algorithm
Šuster, P., Jadlovska, A. (2012) Modeling and control design of magnetic levitation system. u: 10th International Symposium Applied Machine Intelligence and Informatics, Herlany, Slovakia, January, 26. 28., 2012, 295-299
Trisanto, A. (2007) PID Controllers Using Neural Network For Multi-Input Multi-Output Magnetic Levitation System. Electrican Jurnal Rekayasa dan Teknologi Elektro, 1(1): 63-68
Voglis, C., Lagaris, I.E. (2006) A global optimization approach to neural network training. Neural, Parallel and Scientific Computations, 14, 231-240
Wilamowski, B. (2009) Neural network architectures and learning algorithms. IEEE Industrial Electronics Magazines, 3, 4, 56-63