Neural state estimator for complex mechanical part of electrical drive: neural network size and performance of state estimation

• Autorzy: Łuczak D. , Wójcik A.

Identyfikatory

DOI

10.2478/pead-2018-0017

• Języki publikacji: EN

Abstrakty

EN

This paper presents the results of simulation research of an off-line-trained, feedforward neural-network-based state estimator. The investigated system is the mechanical part of an electrical drive characterised by elastic coupling with a working machine, modelled as a dual-mass system. The aim of the research was to find a set of neural network structures giving useful and repeatable results of the estimation. The mechanical resonance frequency of the system has been adopted at the level of 9.3-10.3 Hz. The selected state variables of the mechanical system are load, speed and stiffness torque of the shaft.

Słowa kluczowe

EN

two-mass drive; neural network; simulation studies; non-linear state estimation

• Wydawca: De Gruyter
• Czasopismo: Power Electronics and Drives
• Rocznik: 2018
• Tom: Vol. 3 (38), No. 1
• Strony: 205--216
• Opis fizyczny: Bibliogr. 19 poz., rys., tab.

Twórcy

autor

Łuczak D.

• Poznan University of Technology, Institute of Control, Robotics and Information Engineering, 5 M. Skłodowska-Curie Square 60-965 Poznan, Poland

autor

Wójcik A.

• Poznan University of Technology, Institute of Control, Robotics and Information Engineering, 5 M. Skłodowska-Curie Square 60-965 Poznan, Poland

Bibliografia

• Isermann, R. (1989). State controller and state observer. In: B.W. Dickinson, E.D. Sontag, eds., Digital Control Systems: Volume 1: Fundamentals, Deterministic Control. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 180-227.
• Jobling, C. P., Grant, P. W., Barker, H. A. and Townsend, P. (1994). Object-oriented programming in control system design: a survey. Automatica, 30(8), pp. 1221-1261.
• Kamiński, M. (2013). Estymacja zmiennych stanu układu dwumasowego za pomocą modeli neuronowych. Prace Naukowe Instytutu Maszyn, Napędów i Pomiarów Elektrycznych Politechniki Wrocławskiej, 69(33), pp. 222-238.
• Kazmierkowski, M. P. and Orlowska-Kowalska, T. (2002). NN state estimation and control in converter-fed induction motor drives, Ch. 2. In: Seppo J. Ovaska, Les M. Sztandera, eds. Soft Computing in Industrial Electronics. Heidelberg, Germany: Physica-Verlag, pp. 45-94.
• Kincaid, D. and Cheney, W. (2006). Arytmetyka Komputerowa. In: Stefan Paszkowski, ed., Analiza numeryczna, Warszawa: Wydawnictwo Naukowo-Techniczne, pp. 46-54.
• Łuczak, D. (2014). Mathematical model of multi-mass electric drive system with flexible connection. In: 2014 19th International Conference on Methods and Models in Automation and Robotics MMAR, Miedzyzdroje, Poland, 2-5 September 2014, IEEE, pp. 590-595.
• Łuczak, D. and Nowopolski, K. (2014). Identification of multi-mass mechanical systems in electrical drives. In: 2014 16th International Conference on Mechatronics - Mechatronika, Brno, Czech Republic, 3-5 December 2014, IEEE, pp. 275-282.
• Łuczak, D. and Wójcik, A. (2017). Object-oriented DSP implementation of neural state estimator for electrical drive with elastic coupling. Poznan University of Technology Academic Journals: Electrical Engineering, 91, pp. 395-406.
• Orlowska-Kowalska, T. and Kaminski, M. (2008). Optimization of neural state estimators of the twomass system using OBD method. In: IEEE International Symposium on Industrial Electronics, Cambridge, UK, 30 June-2 July 2008, ISIE, pp. 461-466.
• Orlowska-Kowalska, T. and Kowalski, C. T. (1997). Neural network application for flux and speed estimation in the sensorless induction motor drive. In: Proceedings of the IEEE International Symposium on Industrial Electronics, vol. 3, Guimaraes, Portugal, 7-11 July 1997, Portugal: ISIE, pp. 1253-1258.
• Orlowska-Kowalska, T. and Szabat, K. (2007a). Neural-Network Application for Mechanical Variables Estimation of a Two-Mass Drive System. IEEE Transactions on Industrial Electronics, 54(3), pp. 1352-1364.
• Orlowska-Kowalska, T. and Szabat, K. (2007b). Vibration Suppression in a Two-Mass Drive System Using PI Speed Controller and Additional Feedbacks-Comparative Study. IEEE Transactions on Industrial Electronics, 54(2,3), pp. 1193-1206.
• Reynaldi, A., Lukas, S. and Margaretha, H. (2012). Backpropagation and Levenberg-Marquardt algorithm for training finite element neural network. In: 2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation, Valetta, Malta, 14-16 November 2012, EMS, pp. 89-94.
• Rojas, R. (1996). Neural Networks – A Systematic Introduction, [Online]. Available at: http://page.mi.fu-berlin.de/rojas/neural/ [Accessed 19 Feb. 2016].
• Simoes, M. G. and Bose, B. K. (1995). Neural network based estimation of feedback signals for a vector controlled induction motor drive. IEEE Transactions on Industry Applications, 31(3), pp. 620-629.
• Szabat, K. and Orlowska-Kowalska, T. (2008). Optimization of the two-mass drive dynamics using different compensation feedbacks. In: 11th International Conference on Optimization of Electrical and Electronic Equipment, OPTIM, Brasov, Romania, 22-24 May 2008, IEEE, pp. 19-24.
• Yadaiah, N. and Sowmya, G. (2006). Neural network based state estimation of dynamical systems. In: International Joint Conference on Neural Networks, IJCNN, Vancouver, BC, Canada, 16-21 July 2006, IEEE, pp. 1042-1049.
• Yu, H. and Wilamowski, B. M. (2011). Levenberg-Marquardt training. In: Bogdan M. Wilamowski, J. David Irwin, eds., Industrial Electronics Handbook – vol. 5 Intelligent Systems, 2nd ed. pp. 12-1 to 12-15.
• Zawirski, K., Deskur, J. and Kaczmarek, T. (2012). Automatyka Napędu Elektrycznego. Poznań: Wydawnictwo Politechniki Poznańskiej, pp. 76-100.