Sensorless Current Prediction of a Three-Phase Inverter Using Machine Learning Algorithms

DOI

10.2991/978-94-6463-252-1_66How to use a DOI?

Keywords

Three-phase inverter; Machine Learning Algorithms (MLA); Multilinear Regression; Support Vector Machine; K-Nearest neighbor

Abstract

The inverter is a crucial component and. Its design can be customized to generate single-phase, three-phase, or multiphase outputs, which enables easy adjustments of output voltage and frequency to meet the diverse needs of different loads. Despite the benefits of inverters, practical conditions can lead to imperfect output waves due to various losses. The refinement of the pure sinusoidal output wave is essential for reducing harmonic distortion and improving overall power quality. Inverters have significant importance in industrial applications, with the sinusoidal pulse width modulation (SPWM) technique being a widely employed form of control the output voltage. However, inverter performance can be further improved by applying machine learning algorithms. Machine learning algorithms have made it feasible to develop accurate and efficient methods for improving inverter performance, which in turn enhances overall efficiency and reliability in power systems applications. In this paper, a dataset was generated using MATLAB for a Resistive and Inductive load three-phase inverter, and machine learning algorithms such as Multi-Linear Regression (MLR), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) were applied to estimate output current and predict power losses. These algorithms offer precise solutions for output current estimation and power loss prediction, this removes the requirement for external inverter sensors.

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  - G. Madhu Murali Siran
AU  - K. Naga Sujatha
PY  - 2023
DA  - 2023/11/09
TI  - Sensorless Current Prediction of a Three-Phase Inverter Using Machine Learning Algorithms
BT  - Proceedings of the Second International Conference on Emerging Trends in Engineering (ICETE 2023)
PB  - Atlantis Press
SP  - 653
EP  - 661
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-252-1_66
DO  - 10.2991/978-94-6463-252-1_66
ID  - MadhuMuraliSiran2023
ER  -