Neural Network Controller for Enhancement of Uninterruptible Power Supply Inverter
Vijaya kumar.S1, D.V.Ashok Kumar2, Ch.Sai Babu3
1Mr. Vijaya Kumar S., Lecturer, Department of Electrical and Electronics Engg., K.P.T.C, Karaikal (Puducherry), India.
2Dr. D.V. Ashok Kumar, Principal, Syamaladevi Institute of Technology for Women, Nandyal (Andhra Pradesh), India.
3Dr.Ch. Sai Babu, Director of Admissions, Professor, Department of Electrical and Electronics Engg., JNT University, Kakinada (Andhra Pradesh), India.
Manuscript received on 18 August 2012 | Revised Manuscript received on 25 August 2012 | Manuscript published on 30 August 2012 | PP: 10-16 | Volume-1 Issue-3, August 2012 | Retrieval Number: C0250061312/2012©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Uninterruptible Power Supplies (UPS) are emergency power sources, which have widespread applications in critical equipments, such as computers, automated process controllers and hospital instruments. With rapid growth in the use of high efficiency power converters, more and more electrical loads are nonlinear and generate harmonics. It is a big challenge for a UPS to maintain a high-quality sinusoidal output voltage under a nonlinear loading condition. The conventional methods employ multi-loop control strategies to perform same task. In conventional methods more inputs cannot be given to the controller, though it accounts for better performance under nonlinear conditions, it will increase the complexity of the system. Whereas a neural network controller can accommodate more inputs and learn from data. Neural Networks (NNs) have been employed in many applications in recent years. A neural network is an interconnection of a number of artificial neurons that simulate a biological brain system. It has the ability to approximate nonlinear functions and can achieve higher degree of fault tolerance. NNs have been successfully introduced into power electronics circuits and application of NNs for harmonic elimination of Pulse Width Modulation (PWM) inverters, where a NN replaced a large and memory demanding look-up table to generate the switching angles of a PWM inverter for a given modulation index. This paper aims to study the behavior of UPS inverter under nonlinear loading condition. A neural network based controller is designed and tested for performance enhancement.
Keywords: Neural Networks, Pulse Width Modulation, Uninterruptible Power Supply.
Scope of the Article: Neural Information Processing