Sensorless and Fuzzy Neuro-Network Control of IPMSM Drives for Ship Electric Propulsion

For the control of ship electric propulsion interior permanent-magnet synchronous motor (IPMSM), the position-sensorless observer and based neuro-fuzzy PI controller had been designed, the position sensorless of the flux-observer-based control scheme can obtain an accurate knowledge of the motor magnetic behavior, and lead to good robustness against load variations. A fuzzy basis neuro-network is utilized for online tuning of the PI controller to ensure optimum drive performance. The DC generator simulates the propeller characteristic as the load of the propulsion motor, the proposed observer and controller had been investigated, and they have been carried out in the digital signal process (DSP).

[1]  T. Lipo,et al.  Vector Control and Dynamics of AC Drives , 1996 .

[2]  M. Nasir Uddin,et al.  Fuzzy logic based speed control of an IPM synchronous motor drive , 1999, Engineering Solutions for the Next Millennium. 1999 IEEE Canadian Conference on Electrical and Computer Engineering (Cat. No.99TH8411).

[3]  T. S. Radwan,et al.  Performances of novel fuzzy logic based indirect vector control for induction motor drive , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[4]  Thomas M. Jahns,et al.  Flux-Weakening Regime Operation of an Interior Permanent-Magnet Synchronous Motor Drive , 1987, IEEE Transactions on Industry Applications.

[5]  Thomas A. Lipo,et al.  Field Weakening in Buried Permanent Magnet AC Motor Drives , 1985, IEEE Transactions on Industry Applications.

[6]  G. Pellegrino,et al.  Position-sensorless control of permanent-magnet-assisted synchronous reluctance motor , 2004, IEEE Transactions on Industry Applications.

[7]  Krishnan,et al.  Electric Motor Drives , 2007 .

[8]  Yi Guo,et al.  Design of ship electric propulsion simulation system , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[9]  James M. Keller,et al.  Neural network implementation of fuzzy logic , 1992 .

[10]  Ahmed Rubaai,et al.  Development and implementation of an adaptive fuzzy-neural-network controller for brushless drives , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[11]  Angelo Raciti,et al.  Fuzzy adaptive vector control of induction motor drives , 1997 .