Modelling of a Boost Converter Using Bayesian Regularized Artificial Neural Network

DOI

10.2991/978-94-6463-074-9_13How to use a DOI?

Keywords

Artificial Neural Network; Boost Converter; PI controller; Steady state error; Stability

Abstract

In this work, a Boost converter is modeled using Machine Learning Algorithm. Bayesian Regularized ANN is used in this work for reducing the lengthy cross-validation and the usage of neural networks to fit the data appropriately. First the boost converter is modeled using state space analysis. The stability of the system is observed using frequency response characteristics. It is observed that the system is well stable with the outer voltage control and inner current control. Inductor current and output voltage are taken as state variables. To obtain less steady state error, for different values of duty cycle, appropriate PI controller parameters are tuned and tabulated. It is found that the controller works effectively and tracks the reference voltage of 15 V with a steady state error of 4.459%. Secondly using BR-ANN method the modeling of the boost converter is performed. The steps involved in the process are (i) using the simulated model of the converter, collect data of different system parameters such as the system variables, (ii) classify into input and output parameters, (iii) use BR-ANN in ANN tool box in MATLAB to validate the models with training and testing data sets, (iv) to model the converter for steady state response (v) obtaining Mean Squared Error and Regression plots for analyzing the convergence. It is found the boost converter is modeled with efficacy (i.e. the response obtained is in close to the simulation results) and the obtained results can still be used for optimal performance and to predict fault conditions. MATLAB simulink and ANN tool box set is used for the work.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Satish Kumar Gudey
AU  - B. V. Lakshmana Rao
AU  - D. Akshaya
AU  - Sarath Pavan
AU  - M. Bharat Chandra
PY  - 2022
DA  - 2022/12/05
TI  - Modelling of a Boost Converter Using Bayesian Regularized Artificial Neural Network
BT  - Proceedings of the International Conference on Artificial Intelligence Techniques for Electrical Engineering Systems (AITEES 2022)
PB  - Atlantis Press
SP  - 136
EP  - 147
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-074-9_13
DO  - 10.2991/978-94-6463-074-9_13
ID  - Gudey2022
ER  -