JOURNAL OF

A novel concept of application of Artificial Neural Networks (ANN) for generating the optimum switching functions for the voltage and harmonic control of DC-to-AC bridge inverters is presented. In many research, the neural network is trained off line using the desired switching angles given by the classic harmonic elimination strategy to any value of the modulation index. This limits the utilisability and the precision in other modulation index values. In order to avoid this problem, a new training algorithm is developed without using the desired switching angles but it uses the desired solution of the elimination harmonic equation, i.e. first harmonics are equal to zero. Theoretical analysis of the proposed solving algorithm with neural networks is provided, and simulation results are given to show the high performance and technical advantages of the developed modulator.

[1]  A. M. Gole,et al.  A neural network controlled optimal pulse-width modulated STATCOM , 1999 .

[2]  Bruno Francois.  Orthogonal considerations in the design of neural networks for function approximation , 1996 .

[3]  P. Mehta,et al.  Optimised PWM inverter control using artificial neural networks , 1995 .

[4]  M.P. Kazmierkowski,et al.  A neural network based space vector PWM controller for voltage-fed inverter induction motor drive , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).

[5]  Mohsen Razzaghi,et al.  Harmonic elimination in pulse-width modulated inverters using piecewise constant orthogonal functions , 1997 .

[6]  E.M. Berkouk,et al.  A five-level diode clamped inverter with self-stabilization of the DC-link voltage for grid connection of distributed generators , 2004, 2004 IEEE International Symposium on Industrial Electronics.

[7]  Zhong Du,et al.  A unified approach to solving the harmonic elimination equations in multilevel converters , 2004, IEEE Transactions on Power Electronics.

[8]  Tian-Hua Liu,et al.  Optimum harmonic reduction with a wide range of modulation indexes for multilevel converters , 2002, IEEE Trans. Ind. Electron..

[9]  Frede Blaabjerg,et al.  A simple direct-torque neuro-fuzzy control of PWM-inverter-fed induction motor drive , 2000, IEEE Trans. Ind. Electron..

[10]  J. Sun,et al.  Optimal PWM based on real-time solution of harmonic elimination equations , 1996 .

[11]  S.R. Bowes,et al.  Simple microprocessor implementation of new regular-sampled harmonic elimination PWM techniques , 1990, Conference Record of the 1990 IEEE Industry Applications Society Annual Meeting.

[12]  Robert M. O'Connell,et al.  Experimental evaluation of a novel switch control scheme for an active power line conditioner , 2003, IEEE Trans. Ind. Electron..

[13]  Y. Kawabata,et al.  Novel vector control system using deadbeat controlled PWM inverter with output LC filter , 2002, Conference Record of the 2002 IEEE Industry Applications Conference. 37th IAS Annual Meeting (Cat. No.02CH37344).

[14]  A. M. Trzynadlowski,et al.  Application of neural networks to the optimal control of three-phase voltage-controlled inverters , 1994 .