Power Quality Improvement using Modified Cuk-Converter with Artificial Neural Network Controller Fed Brushless Dc Motor Drive
Ch. Vijaya Sree1, P. Krishna Chaitanya2, B.Rajesh3
1Ch.Vijaya Sree *, EEE Department, Pragati Engineering College, Surampalem, India.
2P. Krishna Chaitanya, EEE Department, Pragati Engineering College, Surampalem, India.
3B. Rajesh, EEE Department, Pragati Engineering College, Surampalem, India.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 08, 2019. | Manuscript published on December 30, 2019. | PP: 3871-3877 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3324129219/2019©BEIESP | DOI: 10.35940/ijeat.B3324.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Power factor rectification converter (PFRC) hinged bridgeless modified CUK (MCUK) converter supplied to brushless DC engine drive utilizing an Artificial Neural Network controller. Presently, alteration for traditional CUK converter can be obtained through adding a voltage multiplier circuit, to decrease converter losses for wide variation of speed to accomplish most extreme Power Factor and to limit the Total Harmonic Distortion (THD). The designed bridgeless PFRC based converter was investigated hypothetically to obtain the circumstances, for example, Power factor (PF) and Total Harmonic Distortion (THD) are assessed and contrasted with traditional Diode Bridge Rectifier hinged CUK converter supplying to brushless DC motor drive and bridgeless altered CUK using PI controller driven brushless DC motor. Here, simulation results uncover that the ANN controllers are viable and productive contrasted with PI controller, as the steady state error when ANN control used is less and the stabilization of the system is better while using it. Additionally in ANN system, the time to perform calculation is less as there are no numerical models. The performance of the designed framework is simulated in MATLAB Simulink environment.
Keywords: Artificial Neural Network (ANN), Brushless DC motor, Modified CUK- converter (M-CUK), Power factor rectification Converter (PFRC).