Performance enhancement of Uninterruptible Power Supply inverter through Neural Network control strategy


Mr.Vijaya kumar.S,D.V.Ashok Kumar,Ch.Sai Babu,



UPS Inverter,Neural Network Controller for the inverter,THD,


This paper proposes to investigate the performance of UPS inverter under linear and non-linear loading conditions. It has been observed that the inverter’s output voltage distorts particularly under non-linear loading conditions. Conventional way of improving the quality of inverter output is through multiple feedback schemes. These conventional schemes also been developed in MatlabSimulink in order to estimate their performance both under linear and nonlinear loading conditions. Though they perform better under linear loading conditions, there seems to be a droop in their performance under non-linear loading conditions. Hence, the proposed neural network controller for the inverter has been designed and tested for the performance enhancement of the UPS inverter both under linear and non-linear conditions. Load variations and reference voltage variation methodologies have been followed for testing the proposed topology under closed loop for improving the performance of UPS inverter.


I. O.Soares, H.Gonçalves, A.Martins, A.Carvalho, “Neural Networks Based
Power Flow Control of the Doubly Fed Induction Generator”, IEEE 2009.
II. S.Buso, S.Fasolo, P.Mattavelli, “Uninterruptible power supply multi-loop
control employing digital predictive voltage and current regulators”, Proc.
IEEE APEC’01, pp: 907–913, 2001.
III. S.Mohagheghi, R.G.Harley, T.G.Habetler, D.Divan, “Condition Monitoring
of Power Electronic Circuits Using Artificial Neural Networks”, IEEE
Transactions on power electronics, Vol.: 24, Issue: 10, October 2009.
IV. W.Liu, L.Liu, D.A.Cartes, X.Wang, “Neural Network Based Controller
Design for Three-Phase PWM AC/DC Voltage Source Converters”,
International Joint Conference on Neural Networks, 2008.
V. X.Sun, H.L.Martin, “Analog Implementation Of a Neural Network Controller
for UPS Inverter Applications”, IEEE Trans. Power Electron., Vol.: 17, pp:
305-313, May 2002.
VI. X.Wang, B.Xu ,L.Ding, “Simulation Study on A Single Neuron PID Control
System of DC/DC Converters”, Workshop on Power Electronics and
Intelligent Transportation System, 2008.
VII. Y.C.Fang, B.W.Wu, “Prediction of the Thermal Imaging Minimum
Resolvable (Circle) Temperature Difference with Neural Network
Application”, IEEE Transactions on pattern analyis and machine
intelligence, Vol.: 30, Issue: 12, Dec. 2008.
VIII. Y.Dong, Y.Wang, Z.Lin, T.Watanabe, “High Performance and Low Latency
Mapping for Neural Network into Network on Chip Architecture”, IEEE
Transactions on power electronics, Vol.: 24, Issue: 10, October 2009.

View | Download