ANN based three-value logic SVPWM control in CSR

To achieve better performance with various load and system parameters in controlling a current-source rectifier (CSR) with less computing cost, a neural-network-based implementation of three-logic space-vector modulation (SVM) is proposed in this research, and the random weight change (RWC)algorithm is employed for on-line parameter tuning. The scheme has been simulated in SABER simulation software and the result is compared with the conventional SVM method. The advantage of the method is explicit with a better performance under a non-rated system load.

[1]  T. Kataoka,et al.  State feedback control of current type PWM AC-to-DC converters , 1991, Conference Record of the 1991 IEEE Industry Applications Society Annual Meeting.

[2]  J. Espinoza,et al.  DSP based space vector PWM pattern generators for current source rectifiers and inverters , 1995, Proceedings 1995 Canadian Conference on Electrical and Computer Engineering.

[3]  J. Espinoza,et al.  A combined artificial neural network and DSP approach to the implementation of space vector modulation techniques , 1996, IAS '96. Conference Record of the 1996 IEEE Industry Applications Conference Thirty-First IAS Annual Meeting.

[4]  Yukihiko Sato,et al.  A current-type PWM rectifier with active damping function , 1995 .

[5]  K. Hirotsu,et al.  An analog neural network chip with random weight change learning algorithm , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[6]  Vladimir A. Katic,et al.  Online control of current-source-type active rectifier using transfer function approach , 2001, IEEE Trans. Ind. Electron..

[7]  Geza Joos,et al.  State variable decoupling and power flow control in PWM current-source rectifiers , 1998, IEEE Trans. Ind. Electron..

[8]  H. van der Broeck,et al.  Analysis and Realization of a Pulse Width Modulator Based on Voltage Space Vectors , 1986, 1986 Annual Meeting Industry Applications Society.

[9]  H. Tuusa,et al.  A vector controlled current-source PWM rectifier with a novel current damping method , 2000 .

[10]  Caisheng Wang,et al.  Analysis of Inductor Current Sharing in Nonisolated and Isolated Multiphase dc–dc Converters , 2007, IEEE Transactions on Industrial Electronics.

[11]  Xiaojie You,et al.  A novel control strategy for current-source rectifiers with space vector modulation , 2008, 2008 IEEE Power Electronics Specialists Conference.

[12]  Thomas G. Habetler,et al.  A fast on-line neural network training algorithm for a rectifier regulator , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.

[13]  B.K. Bose,et al.  A neural network based space vector PWM controller for a three-level voltage-fed inverter induction motor drive , 2001, Conference Record of the 2001 IEEE Industry Applications Conference. 36th IAS Annual Meeting (Cat. No.01CH37248).

[14]  J. Doval‐Gandoy,et al.  Dynamic and steady state analysis of a three phase buck rectifier , 2000 .