Adaptive fuzzy-neural-network control for induction spindle motor drive

An induction spindle motor drive using synchronous pulse width modulation (PWM) and dead-time compensatory techniques with an adaptive fuzzy neural-network controller (AFNNC) is proposed in this study for advanced spindle motor applications. First, the operating principles of a new synchronous PWM technique and the circuit of dead-time compensator are described in detail. Then, since the control characteristics and motor parameters for high speed operated induction spindle motor drive are time-varying, an AFNNC is proposed to control the rotor speed of the induction spindle motor. In the proposed controller, the induction spindle motor drive system is identified by a fuzzy neural-network identifier (FNNI) to provide the sensitivity information of the drive system to an adaptive controller. The back-propagation algorithm is used to train the FNNI online. Moreover, the effectiveness of the proposed induction spindle motor drive system is demonstrated using some simulated and experimental results.

[1]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[2]  Seung-Gi Jeong,et al.  The analysis and compensation of dead-time effects in PWM inverters , 1991 .

[3]  Faa-Jeng Lin.  Fuzzy adaptive model-following position control for ultrasonic motor , 1997 .

[4]  K. Kamiyama,et al.  Fully digital, vector-controlled PWM VSI-fed AC drives with an inverter dead-time compensation strategy , 1988, Conference Record of the 1988 IEEE Industry Applications Society Annual Meeting.

[5]  R. C. Dodson,et al.  Compensating for dead time degradation of PWM inverter waveforms , 1990 .

[6]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control - design and stability analysis , 1994 .

[7]  Russel J. Kerkman,et al.  Pulse-based dead-time compensator for PWM voltage inverters , 1997, IEEE Trans. Ind. Electron..

[8]  Werner K. Volkmann,et al.  AC Spindle Drives for Machine Tools , 1985, IEEE Transactions on Industry Applications.

[9]  J. Y. Yoo,et al.  Dead time compensation in a vector-controlled induction machine , 1998, PESC 98 Record. 29th Annual IEEE Power Electronics Specialists Conference (Cat. No.98CH36196).

[10]  Yie-Chien Chen,et al.  A model reference control structure using a fuzzy neural network , 1995 .

[11]  A. Morris,et al.  Fuzzy neural networks for nonlinear systems modelling , 1995 .

[12]  Tsu-Tian Lee,et al.  On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[13]  T. Sawa,et al.  A high-speed vector-controlled spindle motor drive with closed transition between with encoder control and without encoder control , 1992 .

[14]  Tore Undeland,et al.  Power Electronics: Converters, Applications and Design , 1989 .

[15]  Hong Wang,et al.  A direct adaptive neural-network control for unknown nonlinear systems and its application , 1998, IEEE Trans. Neural Networks.

[16]  Aldo Boglietti,et al.  Test procedure for very high speed spindle motors , 1995 .

[17]  P. S. Sastry,et al.  Memory neuron networks for identification and control of dynamical systems , 1994, IEEE Trans. Neural Networks.

[18]  Faa-Jeng Lin,et al.  Control of indirect field-oriented induction motor drives considering the effects of dead-time and parameter variations , 1993, IEEE Trans. Ind. Electron..