Affiliation:
1. Islamic Azad University
Abstract
This approach is carry out for developing the Adaptive Neuro-Fuzzy Inference System (ANFIS) for controlling the forthcoming Intelligent Universal Transformer (IUT) in regard of voltages and current control in both input and output stages which is optimized by particle swarm optimization. Current or voltages errors and their time derivative have been considered as the inputs of Nero Fuzzy controller for elaborating the firing angles of converters in IUT basic construction. ANFIS constructed from a fuzzy inference system (FIS) in which the membership function parameters are tuned according to the back propagation algorithm or in conjunction to the least squares method. A neural network maps inputs through input membership functions and associated parameters, and output membership functions and associated parameters to outputs which interprets the input-output map. The associated parameters of membership functions change through the learning algorithm by a gradient vector modeling the input output data in case of given parameters. Optimization method will be investigated to adjust the parameters according to error reduction computed by sum of the squared variation from actual outputs to the desired ones. Advanced Distribution Automation (ADA) is the state of art introducing for tomorrows distribution automation with the new invention in management and control. ADA is equipping by the Intelligent Equipment Devices (IED) in which IUT is a key point introducing as an intelligent transformer subjecting for tomorrows distribution automation in the near future. The proposed ANFIS is a control scheme develop for controlling the IUT by bringing the major advantages like harmonic Filtering, voltage regulation, automatic sag correction, energy storage, 48V DC option, three phase outputs in term of one phase input, reliable divers power as 240V 400HZ for communication utilization and two other 240V 60 HZ outputs, dynamic system monitoring and robustness in major disturbances occurred in terms of input and load variation.
Publisher
Trans Tech Publications, Ltd.
Reference15 articles.
1. B. Allaoua, A. LAOUFI, B. Gasbaoui, A. Abderrahmani, Neuro-Fuzzy DC Motor Speed Control Using Particle Swarm Optimization, Leonardo Electronic Journal of Practices and Technologies, 15, July-December (2009).
2. EPRI Product ID # 1009516, Feasibility Study for the Development of High-Voltage, Low-Current Power Semiconductor Devices, 2003 Strategic Science and Technology Project.
3. F. Goodman, Intelligent Universal Transformer Technology Development, EPRI (2006).
4. IEEE Power Engineering Society, Research Plan for Advanced Distribution Automation, General Meeting, (2005).
5. M. Mc. Granaghan, F. Goodman, Technical and System Requirements for Advanced Distribution Automation, 18th International Conference on Electricity Distribution, CIRED, Turin, 6-9 June (2005).