Friday , March 29 2024

Real Time Analysis of Positive Output Super Lift Converter
Using ANN Controller

V. VENKATESH1*, C. KAMALAKANNAN2

1 Research Scholar, Department of Electrical and Electronics Engineering,
St.Peter’s University, Chennai, India
vvvsh1986@gmail.com

* Corresponding author

Professor, Department of Electrical and Electronics Engineering,
Rajalakshmi Engineering College, Chennai, India

Abstract: The Artificial neural network controller is used for controlling any electrical and electronic system using the logical method. The controller performs the logical function by utilizing the unique learning algorithms. The application of artificial neural network controller in positive output super lift converter enables the system to maintain the stability, reliability, and performance during the input-output parameterization. The hardware and simulation works are carried out in this proposed model. The comparative study with existing controller models is impacted. In all such cases, the ability of the super lift converter system using artificial neural network controller yields the best in class performance, stability and efficiency for both line and load variation.

Keywords: stability of super lift converter, hardware efficiency of super lift converter, a performance comparison of the converter, comparative study on converters.

>>Full text
CITE THIS PAPER AS:
V.
VENKATESH*, C. KAMALAKANNAN, Real Time Analysis of Positive Output Super Lift Converter Using ANN Controller, Studies in Informatics and Control, ISSN 1220-1766, vol. 25(3), pp. 323-334, 2016. https://doi.org/10.24846/v25i3y201606

1. Introduction

Intelligent control is a class of control techniques that use the various artificial intelligence of computing approaches like neural networks, fuzzy logic, machine learning, evolutionary computation and genetic algorithm. Artificial neural networks are a family of the model developed using machine learning [3,7]. This ANN is used to determine the approximate functions for larger inputs [4,9]. ANN is the system of interconnected neurons which exchanges the information with neighbouring neurons.

The each neuron in the ANN possesses numeric weights which are tuned to the desired value using various learning methods [2]. The inputs are modulated in ANN based on these neurons numeric value and yields the corresponding output. This sort of ANN system performs as a controller for any application system [13].

The voltage level of a Direct Current (DC) can be converted from one voltage level to another voltage level by a power electronic circuit called DC to DC converter [5]. The DC to DC converter generates the DC output voltage for the given DC input voltage. The essential requirements for a good DC to DC converter are to provide a high voltage transfer gain, to reduce the occurrence of Alternating Current (AC) ripple voltage in the DC output voltage, to provide good isolation between the input source and load, and to regulate the output DC voltage from line and load variation efficiently.

A new series of DC to DC converter which satisfies all the essential requirements of DC to DC converter is Positive Output Super Lift converter (POSLC). This converter implies the voltage lift technique which produces the positive to positive voltage conversion with a higher proportion of voltage transfer gain.

Theoretically, the elementary DC to DC converters can achieve a high step up voltage transfer gain with an extremely high duty cycle. Unfortunately, in practice, the step-up voltage gain is limited because of the effect of power switches, rectifier diodes, and the Equivalent Series Resistance (ESR) of inductors and capacitors which account for heavy conduction losses. Moreover, the extremely high duty cycle operation will result in a serious reverse recovery problem.

Each functional cell of the super lift converters utilizes the Voltage Lift (VL) technique, which is an efficient method widely applied in electronic circuit design, to realize the performance improvement. In this converter voltage unit cells in cascade connection and the transformerless single-switch operation are successfully implemented to provide a very high step up voltage transfer gains. Super lift technique has been developed which performs the output voltage increasing stage by stage along in geometric progression.

In a design and implementation solution, the analysis on their mathematical modeling and control strategies is necessary to promote the practical applications of super lift DC to DC converter. The derived Transfer function for the split capacitor type elementary additional series positive output super lift converter helps to control and maintain the stability of the system. The Artificial Neural Network Controller (ANNC) is designed for controlling the SEPOSLC converter. The neurons in ANNC are trained by utilizing the values of transfer function [9,12]. The neurons are trained up by an online learning algorithm.

The design of artificial neural network controller benefits the SEPOSLC converter with a high line and load variation robustness and high stability.

REFERENCES

  1. ELBULUK M. E., H. W. CHAN, I. HUSAIN., Neural Network Controllers for Power Factor Correction of AC/DC Switching Converters, Industry App. Conference, 1998, pp. 1617-1624.
  2. HASSAN, M., G. KOTHAPALLI., Comparison between Neural Networks based PI and PID Controllers, Proceedings of International Multi Conference on Systems, Signals & Devices. Amman, Jordan, 2012, pp. 1-6.
  3. SUSNEA, I.,Distributed Neural Networks Microcontroller Implementation and Applications, Studies in Informatics and Control, vol. 21(2), 2012, pp. 165-172.
  4. KOTHAPALLI, G., Y. H. MOHAMMED, Design of a Neural Network based Intelligent PI Controller for a Pneumatic System, IJCS, 2008.
  5. CHENG, K.-H., C.-F. HSU, C.-M. LIN, T.-T. LEE, C. LI., Fuzzy-Neural Sliding-Mode Control for DC-DC Converters Using Asymmetric Gaussian Membership Functions, IEEE Transaction on Industrial Electronics, vol. 54 (3), 2007, pp. 1528-1536.
  6. LEYVA, R., L. MARTINEZ-SALAMERO, B. JAMMES, J. C. MARPINARD, F. GUINJOAN, Identification and Control of Power Converters by Means of Neural Networks, IEEE Trans. on Industrial App., August, vol. 44 (8), 1997, pp. 735-742.
  7. LUO, F. L., Luo Converters-voltage Lifts Technique, Proceedings of the IEEE Power Electronics special conference IEEE-PESC, Fukuoka, Japan. 1998, pp. 1783-1789.
  8. LUO, F. L., H. YE., Positive Output Super Lifts Converters, IEEE Trans. on Power El., vol. 18(1), 2003, pp. 105-113.
  9. MAHDAVI, J., M. R. NASIRI, A. AGAH, A. EMADI, Application of Neural Networks and State-space Averaging to DC/DC PWM Converters in Sliding-Mode Operation, IEEE Transaction on Mechatronics, vol. 10(1), 2005, pp. 60-67.
  10. OFOLI, A. R., A. RUBAAI., Real-time Implementation of a Fuzzy Logic Controller for Switch-mode Power-stage DC–DC Converters, IEEE Transaction on Industrial Applications, November/ December, vol. 42(6), 2006, pp.1367-1374.
  11. RICHER E., Y. HURMUZLU., A High Performance Force Actuator System Part-2: Nonlinear Controller Design, ASME Journal of Dynamic Systems Measurement and Control, vol. 122(3), 2000, pp. 426-434.
  12. RUBAAI, A., A. R. OFOLI, L. BURGE, M. , Hardware Implementation of an Adaptive Network-based Fuzzy Controller for DC-DC Converters, IEEE Transaction on Industrial Applications, Nov/Dec, vol. 41(6), 2005, pp. 1557- 1565.
  13. UTOMO, W. M., A. BAKAR, M. AHMAD, T. TAUFIK, R. HERIANSYAH., Online Learning Neural Network Control of Buck-Boost Converter, 8th Conference on Information Technology: New Generations, 2011, pp. 485-489.
  14. WANG X., Y. CHENG, W. SUN., Multi-step Predictive Control with TDBP Method for Pneumatic Position Servo System, Transaction of the Institute of Measurement and Control, 2006, pp. 28-53.