Back-EMF Based Rotor Position Estimation for Low Cost PMSM Drive Using Fully Connected Cascade Artificial Neural Networks

Gabriel H. Negri; Filipe G. Nazário; José de Oliveira; Ademir Nied

doi:10.18618/REP.2018.1.2728

Authors

Gabriel H. Negri Santa Catarina State University, Joinville – SC, Brazil
Filipe G. Nazário Santa Catarina State University, Joinville – SC, Brazil
José de Oliveira Santa Catarina State University, Joinville – SC, Brazil
Ademir Nied Santa Catarina State University, Joinville – SC, Brazil

DOI:

https://doi.org/10.18618/REP.2018.1.2728

Keywords:

Artificial Neural Networks, Back-EMF Estimation, Permanent Magnet Synchronous Motor, Position Estimation

Abstract

Permanent Magnet Synchronous Motors (PMSMs) are widely used mainly due to their high torque per volume, high efficiency and low maintenance cost, among other advantages. To perform the vector control on rotor speed and stator currents, the feedback of those variables is necessary, which can be done directly or by estimation. Measuring rotor position and speed directly requires the use of a mechanical device attached to the motor shaft, increasing the drive system volume and its maintenance cost. To overcome such disadvantages, many sensorless methods for speed estimation have been proposed. Among those methods, various strategies based on Artificial Neural Networks (ANNs) can be found. This paper presents a back-electromotive force estimator based on Fully Connected Cascade ANNs (FCC-ANNs). From the estimator, rotor position and speed can be obtained. Simulation and experimental results using automatically generated C code functions for the FCC-ANNs using fixed point notation provided rotor position estimation with simple implementation.

Downloads

Download data is not yet available.

Author Biographies

Gabriel H. Negri, Santa Catarina State University, Joinville – SC, Brazil

born in March 12, 1992, in Joinville-SC, is an Electrical Engineer (2015) and Master (2016) with Santa Catarina State University. His areas of interest are predictive control, robotics and machine learning.

Filipe G. Nazário, Santa Catarina State University, Joinville – SC, Brazil

born on October 20, 1982, in Criciúma-SC, is an Electrical Engineer (2008), Master (2014) and is currently working at Embraco, developing controls for hermetic compressor refrigeration industry. His areas of interest are electrical machines, sensorless motor control solutions and embedded software development.

José de Oliveira, Santa Catarina State University, Joinville – SC, Brazil

born in 06/15/1961 in Mandaguari-PR, is an Electrical Engineer (1986), Master (1994) and Doctor in Electrical Engineering (2000) with the Federal University of Santa Catarina. He is currently an associate professor with the Department of Electrical Engineering, Santa Catarina State University. His areas of interest are control systems, electrical machine actuation and power electronics.

Ademir Nied, Santa Catarina State University, Joinville – SC, Brazil

born in 06/12/1962 in Santo Ângelo-RS, is an Electrical Engineer (1987), Master (1995) and Doctor in Electrical Engineering (2007) with Federal University of Minas Gerais. He is currently an associate professor with the Department of Electrical Engineering, Santa Catarina State University. His areas of interest are electrical machines, control of electrical drives and neural networks.

References

F. Betin, G.-A. Capolino, D. Casadei, B. Kawkabani,R. I. Bojoi, L. Harnefors, E. Levi, L. Parsa, B. Fahimi," Trends in Electrical Machines Control: Samples for Classical, Sensorless and Fault-Tolerant Techniques", IEEE Industrial Electronics Magazine, vol. 8, no. 2,pp. 43-55, June 2014.https://doi.org/10.1109/MIE.2014.2313752 DOI: https://doi.org/10.1109/MIE.2014.2313752

T. D. Batzel, K. Y. Lee, "An Approach to Sensorless Operation of the Permanent-Magnet Synchronous Motor Using Diagonally Recurrent Neural Networks", IEEE Transactions on Energy Conversion, vol. 18,no. 1, pp. 100-106, February 2003.https://doi.org/10.1109/TEC.2002.808386 DOI: https://doi.org/10.1109/TEC.2002.808386

A. G. Bartsch, G. H. Negri, C. R. Scalabrin, M. S. M.Cavalca, A. Nied, J. de Oliveira, "Predictive ControlApproach for Permanent Magnet Synchronous Motor Drive",Eletrônica de Potência, vol. 20, no. 4, pp. 395-403, November 2015.https://doi.org/10.18618/REP.2015.4.2567 DOI: https://doi.org/10.18618/REP.2015.4.2567

M. Pacas, "Sensorless Drives in Industrial Applications: Advanced Control Schemes", IEEE Industrial Electronics Magazine, vol. 5, no. 2, pp.16-23, June 2011.https://doi.org/10.1109/MIE.2011.941125 DOI: https://doi.org/10.1109/MIE.2011.941125

J. C. G. Real, E. V. Sánchez, J. G. Gil, "Position and Speed Control of Brushless DC Motors Using Sensorless Techniques and Application Trends", Sensors, vol. 10, no. 7, pp. 6901-6947, July 2010.https://doi.org/10.3390/s100706901 DOI: https://doi.org/10.3390/s100706901

S. Wu, Y. Wang, S. Cheng, "Extreme learningmachine based wind speed estimation and sensorles scontrol for wind turbine power generation system", Neurocomputing, vol. 102, pp. 163-175, February2013.https://doi.org/10.1016/j.neucom.2011.12.051 DOI: https://doi.org/10.1016/j.neucom.2011.12.051

J. M. G. Villalobos, J. R. Resendiz, E. A. R. Araiza,V. H. Mucino, "A review of parameter estimators and controllers for induction motors based on artificial neural networks”, Neurocomputing, vol. 118, pp. 87-100, October 2013.https://doi.org/10.1016/j.neucom.2013.02.018 DOI: https://doi.org/10.1016/j.neucom.2013.02.018

B. Karanayil, M. F. Rahman, C. Grantham, "Online Stator and Rotor Resistance Estimation Scheme Using Artificial Neural Networks for Vector Controlled Speed Senseless Induction Motor Drive", IEEE Transactions on Industrial Electronics, vol. 54, no. 1,pp. 167-176, February 2007.https://doi.org/10.1109/TIE.2006.888778 DOI: https://doi.org/10.1109/TIE.2006.888778

B. L. G. Costa, B. A. Angélico, A. Goedtel, M. F.Castoldi, C. L. Graciola, "Differential Evolution Applied to DTC Drive for Three-Phase Induction Motors Using an Adaptive State Observer", Journal of Control, Automation and Electrical Systems, vol. 26,no. 4, pp. 403-420, August 2015.https://doi.org/10.1007/s40313-015-0188-0 DOI: https://doi.org/10.1007/s40313-015-0188-0

L. J. S. Shanthi, R. Arumugam, Y. K. Taly, "A novel rotor position estimation approach for an 8/6 solid rotor switched reluctance motor", Neural Computing and Applications, vol. 21, pp. 461-468, April 2012.https://doi.org/10.1007/s00521-010-0447-8 DOI: https://doi.org/10.1007/s00521-010-0447-8

K. Premkumar, B. V. Manikandan, "Adaptive Neuro-Fuzzy Inference System based speed controller for brushless DC motor”, Neurocomputing, vol. 138, pp.260-270, August 2014.https://doi.org/10.1016/j.neucom.2014.01.038 DOI: https://doi.org/10.1016/j.neucom.2014.01.038

M. George, K. P. Basu, A. T. W. Chiat, "Model reference controlled separately excited DC motor", Neural Computing and Applications, vol. 19, pp. 343-350, April 2010.https://doi.org/10.1007/s00521-009-0271-1 DOI: https://doi.org/10.1007/s00521-009-0271-1

K. Patan, "Neural Network-Based Model Predictive Control: Fault Tolerance and Stability",IEEE Transactions on Control Systems Technology, vol. 23,no. 3, pp. 1147-1155, May 2015.https://doi.org/10.1109/TCST.2014.2354981 DOI: https://doi.org/10.1109/TCST.2014.2354981

M. H. Terra, M. Bergerman, R. Tinós, A. A. G.Siqueira, "Controle Tolerante a Falhas de Robôs Manipuladores", SBA Controle e Automação, vol. 12,no. 2, pp. 73-92, August 2001.

E. R. Marcelo G. Villalva, "Neural Networks Applied to the Control of a Four-Wire Shunt Active Power Filter", Eletrônica de Potência, vol. 10, no. 1, pp. 23-30, June 2005.https://doi.org/10.18618/REP.2005.1.023030 DOI: https://doi.org/10.18618/REP.2005.1.023030

C. Olivieri, M. Tursini, "A novel PLL scheme for a sensorless PMSM drive overcoming common speed reversal problems", in International Symposium on Power Electronics, Electrical Drives, Automation and Motion, pp. 1051-1056, 2012.https://doi.org/10.1109/SPEEDAM.2012.6264468 DOI: https://doi.org/10.1109/SPEEDAM.2012.6264468

B. M. Wilamowski, "Neural Network Architectures and Learning Algorithms", IEEE Industrial Electronics Magazine, vol. 3, no. 4, pp. 56-63,December 2009.https://doi.org/10.1109/MIE.2009.934790 DOI: https://doi.org/10.1109/MIE.2009.934790

P. C. Krause, R. R. Nucera, R. J. Krefta, O. Wasynczuk,"Analysis of a Permanent Magnet Synchronous Machine Supplied from a 180oInverter With Phase Control", IEEE Transactions on Energy Conversion, vol. EC-2, no. 3, pp. 423-431, September 1987.https://doi.org/10.1109/TEC.1987.4765868 DOI: https://doi.org/10.1109/TEC.1987.4765868

D. Grenier, J.-P. Louis, "Use of an extension of the Park's transformation to determine control laws applied to a non-sinusoidal permanent magnet synchronous motor", in Fifth European Conference on Power Electronics and Applications, pp. 32-37, 1993.

E. Sperb, L. Negri, A. Baasch, H. Polli, J. de Oliveira,A. Nied, "Senseless control of PMSM using anew efficient neural network speed estimator”, in International Conference on Power Engineering, Energy and Electrical Drives (POWERENG), pp. 1-5,2011.https://doi.org/10.1109/PowerEng.2011.6036447 DOI: https://doi.org/10.1109/PowerEng.2011.6036447

L. H. Negri, “SuperNN”, 2014. [Online]. Available at:https://bitbucket.org/lucashnegri/supernn