Published
Evaluating neural control with optimal architecture for DC/DC converter
Evaluación de control neuronal con arquitectura óptima para convertidor DC/DC
DOI:
https://doi.org/10.15446/ing.investig.v29n3.15196Keywords:
control, electrical energy conversion, DC/DC converter, intelligent system (en)control, conversión de energía eléctrica, convertidores DC/DC, sistemas inteligentes (es)
Downloads
Controlling DC/DC converters (topologies widely used in the active reduction of harmonic content for single-phase nonlinear low-power equipment) raises great design challenges due to the mathematical model's complexity and its highly nonlinear dynamic characteristics. Artificial intelligence techniques, such as neuronal networks, suppose great improvements in design and final performance, given their capacity for learning complex dynamics and generalising their behaviour. This work was aimed at proposing (and evaluating dynamic response later on) direct control link with neuronal networks which also allowed eliminating test elements and error in its design. Artificial neuronal network-based direct control was designed as well as possible using bioinspired search models. This simultaneously optimized two different but fundamental aspects of the network: architecture and the weight of the connections. The control was applied to a boost converter. The results led to observing the scheme's dynamic performance; response time and exit voltage delta led to concluding that the criteria selected for designing the control were appropriate and represented a contribution towards developing control applications of DC/DC switchmode systems.
El control de convertidores DC/DC, topologías utilizadas ampliamente en la reducción activa de contenido armónico para equipo monofásico no lineal de baja potencia, plantea grandes retos de diseño debido a lo complejo del modelo matemático y su característica dinámica altamente no lineal. Técnicas de inteligencia artificial como las redes neuronales, suponen grandes mejoras en el diseño y desempeño final, dada su capacidad de aprender dinámicas complejas y generalizar su comportamiento. La motivación de este trabajo fue la de plantear (y posteriormente evaluar la respuesta dinámica) un lazo de control directo con redes neuronales, que permitiera adicionalmente eliminar elementos de prueba y error en su diseño. Se propone un control directo basado en red neuronal artificial, cuyo diseño se realizó de forma óptima utilizando modelos de búsqueda bioinspirada, esto para optimizar simultáneamente dos aspectos diferentes pero fundamentales de la red: la arquitectura y los pesos de las conexiones. El control es aplicado a un convertidor boost. Los resultados obtenidos permiten observar el desempeño dinámico del esquema, para el cual los tiempos de respuesta y los delta de voltaje en la salida permiten concluir que los criterios seleccionados para el diseño del control son apropiados y representan un aporte en el desarrollo de aplicaciones de control de sistemas conmutados DC/DC.
References
Haupt, R. L., Haupt, S. E., Practical genetic algorithms., Second edition, Wiley-Interscience, Canada, 2004.
Khoshooei, A., Moghani, J. S., Implementation of a Single Input Fuzzy Controller for a High Power Factor Boost Converter., IEEE AFRICON, 7th Africon conference in Africa, Technology innovation, Gaborone, Botswana, September 2004, pp. 69-72.
Martínez, F. H., Documento final del proyecto de investigación: Evaluación de estructuras digitales para el diseño de sistemas de control difuso (sin publicar, 2008)., Universidad Distrital, Grupo de investigación ARMOS, Bogotá D.C., 2008.
Martinez, F. H., Gómez, D. F., Fuzzy logic controller for boost converter with active power factor correction., 7th International Conference on Power Electronics ICPE'07, Daegu, Korea, Oct. 2007, pp. 936-940.
Russell, S. J., Norvig, P., Inteligencia artificial, un enfoque moderno., Segunda edición, Pearson Prentice Hall, Madrid, 2004, pp.126-135.
Shepherd, W., Zhang, L., Power Converter Circuits., Marcel Dekker Inc., New York, 2004.
Subramanyam, V., Srinivasan, D., Oruganti, R., A dual layered PSO algorithm for evolving an artificial neural network controller., IEEE Congress on Evolutionary Computation CEC 2007, Singapore, 2007, pp. 2350-2357.
Tsoy, Y. R., Spitsyn, V. G., Using genetic algorithm with adaptive mutation mechanism for neural networks design and training., Proceedings The 9th Science and Technology KORUS 2005, pp.709-714.
Whitley, D., Genetic algorithms and neural networks., Genetic Algorithms in Engineering and Computer Science, Winter, Periaux, Galan and Cuesta, Eds. John Wiley, 1995, pp. 203-216.
Dimensions
PlumX
Article abstract page views
Downloads
How to Cite
License
Copyright (c) 2009 Fredy Hernán Martínez Sarmiento, Mariela Castiblanco Ortíz
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors or holders of the copyright for each article hereby confer exclusive, limited and free authorization on the Universidad Nacional de Colombia's journal Ingeniería e Investigación concerning the aforementioned article which, once it has been evaluated and approved, will be submitted for publication, in line with the following items:
1. The version which has been corrected according to the evaluators' suggestions will be remitted and it will be made clear whether the aforementioned article is an unedited document regarding which the rights to be authorized are held and total responsibility will be assumed by the authors for the content of the work being submitted to Ingeniería e Investigación, the Universidad Nacional de Colombia and third-parties;
2. The authorization conferred on the journal will come into force from the date on which it is included in the respective volume and issue of Ingeniería e Investigación in the Open Journal Systems and on the journal's main page (https://revistas.unal.edu.co/index.php/ingeinv), as well as in different databases and indices in which the publication is indexed;
3. The authors authorize the Universidad Nacional de Colombia's journal Ingeniería e Investigación to publish the document in whatever required format (printed, digital, electronic or whatsoever known or yet to be discovered form) and authorize Ingeniería e Investigación to include the work in any indices and/or search engines deemed necessary for promoting its diffusion;
4. The authors accept that such authorization is given free of charge and they, therefore, waive any right to receive remuneration from the publication, distribution, public communication and any use whatsoever referred to in the terms of this authorization.
