Optimisation of neural state variables estimators of two-mass drive system using the Bayesian regularization method

• Autorzy: Kamiński M. , Orłowska-Kowalska T.
• Języki publikacji: EN

Abstrakty

EN

The paper deals with the application of neural networks for state variables estimation of the electrical drive system with an elastic joint. The torsional vibration suppression of such drive system is achieved by the application of a special control structure with a state-space controller and additional feedbacks from mechanical state variables. Signals of the torsional torque and the load-machine speed, estimated by neural networks are used in the control structure. In the learning procedure of the neural networks a modified objective function with the regularization technique is introduced. For choosing the regularization parameters, the Bayesian interpretation of neural networks is used. It gives a possibility to calculate automatically these parameters in the learning process. In this work results obtained with the classical Levenberg-Marquardt algorithm and the expanded one by a regularization function are compared. High accuracy of the reconstructed signals is obtained without the necessity of the electrical drive system parameters identification. Simulation results show good precision of both presented neural estimators for a wide range of changes of the load speed and torque. Simulation results are verified by the laboratory experiments.

Słowa kluczowe

EN

electrical drive; two-mass system; state estimation; neural networks; training methods; Bayesian regularization

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2011
• Tom: Vol. 59, nr 1
• Strony: 33--38
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Kamiński M.

autor

Orłowska-Kowalska T.

• Institute of Electrical Machines, Drives and Measurements, Wroclaw Institute of Technology, 19 Smoluchowskiego St., 50-372 Wrocław, Poland,

Bibliografia

• [1] M. Cristea and A. Dinu, “A new neural networks approach to induction motor speed control”, IEEE Power Electronics Specialists Conf. 2, 784–787 (2001).
• [2] M.F.S.V. D’Angel and P.P. Costa, “State estimation for induction machines using a neural network back-propagation technique”, IEEE Int. Conf. on Systems, Man, and Cybernetics 4, 2613–2618 (2000).
• [3] L.M. Grzesiak and J. Sobolewski, “Energy flow control system based on neural compensator in the feedback path for autonomous energy source”, Bull. Pol. Ac.: Tech. 54, (3), 335–340 (2006).
• [4] J. Korbicz, “Robust fault detection using analytical and soft computing methods”, Bull. Pol. Ac.: Tech. 54, (1), 75–88 (2006).
• [5] G. Zhang and J. Furusho, “Speed control of two-inertia system by PI/PID control”, IEEE Trans. on Industrial Electronic 47 (3), 603–609 (2000).
• [6] T. Orlowska-Kowalska and K. Szabat, “Vibration suppression in two-mass drive system using PI speed controller and additional feedbacks – comparative study”, IEEE Trans. Ind. Electronics 54 (2), 1193–1206 (2007).
• [7] K. Szabat, T. Orlowska-Kowalska, and K. Dyrcz, “Extended Kalman filters in the control structure of two-mass drive system”, Bull. Pol. Ac.: Tech. 54 (3), 315–325 (2006).
• [8] D.R. Hush and B.G. Horne, “Progress in supervised neural networks”, IEEE Signal Processing Magazine 10 (1), 8–39 (1993).
• [9] D.J.C. MacKay, “Bayesian Interpolation”, Neural Computation 4 (3), 415–447 (1992).
• [10] D.J.C. MacKay, “A practical Bayesian framework for backpropagation networks”, Neural Computation 4 (3), 448–472 (1992).
• [11] F. Dan Foresee and M.T. Hagan, “Gauss-Newton approximation to Bayesian learning”, IEEE Int. Conf. on Neural Networks 3, 1930–1935 (1993).
• [12] D. Mirikitani and N. Nikolaev, “Recursive Bayesian Levenberg-Marquardt training of recurrent neural networks”, Int. Joint Conf. on Neural Networks 1, 282–287 (2007).
• [13] R. Gencay and M. Qi, “Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging”, IEEE Trans. Ind. Electronics 12 (4), 726–734 (2001).
• [14] K.K. Aggarwal, Y. Singh, P. Chandra, and M. Puri, “Bayesian regularization in a neural network model to estimate lines of code using function points”, J. Computer Sciences 1 (4), 505–509 (2005).
• [15] T. Orlowska-Kowalska, M. Kaminski, and K. Szabat, “Mechanical state variable estimation of the drive system with elastic coupling using optimised MLP neural networks”, Bull. Pol. Ac.: Tech. 56 (3), 239–246 (2008).
• [16] C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, Oxford, 1996.
• [17] F. Girosi, M. Jones, and T. Poggio, “Regularization theory and neural networks architectures”, Neural Computation 7 (2), 219–269 (1995).