Artificial Neural Network for PWM Rectifier Direct Power Control and DC Voltage Control

Artificial Neural Network for PWM Rectifier Direct Power Control and DC Voltage Control

Arezki Fekik (Akli Mohand Oulhadj University, Bouira, Algeria), Hakim Denoun (University Mouloud Mammeri of Tizi-Ouzou, Algeria), Ahmad Taher Azar (Benha University, Egypt & Nile University, Egypt), Mustapha Zaouia (University Mouloud Mammeri of Tizi-Ouzou, Algeria), Nabil Benyahia (University Mouloud Mammeri of Tizi-Ouzou, Algeria), Mohamed Lamine Hamida (University Mouloud Mammeri of Tizi-Ouzou, Algeria), Nacereddine Benamrouche (University of Tizi Ouzou, Algeria) and Sundarapandian Vaidyanathan (Vel Tech University, India)
Copyright: © 2018 |Pages: 31
DOI: 10.4018/978-1-5225-4077-9.ch010
OnDemand PDF Download:
No Current Special Offers


In this chapter, a new technique has been proposed for reducing the harmonic content of a three-phase PWM rectifier connected to the networks with a unit power factor and also providing decoupled control of the active and reactive instantaneous power. This technique called direct power control (DPC) is based on artificial neural network (ANN) controller, without line voltage sensors. The control technique is based on well-known direct torque control (DTC) ideas for the induction motor, which is applied to eliminate the harmonic of the line current and compensate for the reactive power. The main idea of this control is based on active and reactive power control loops. The DC voltage capacitor is regulated by the ANN controller to keep it constant and also provides a stable active power exchange. The simulation results are very satisfactory in the terms of stability and total harmonic distortion (THD) of the line current and the unit power factor.
Chapter Preview

1. Introduction

Recently, different control approaches have been proposed for designing nonlinear systems for many practical applications, such as optimal control, nonlinear feedback control, adaptive control, sliding mode control, nonlinear dynamics, chaos control, chaos synchronization control, fuzzy logic control, fuzzy adaptive control, fractional order control, and robust control and their integrations (Azar & Vaidyanathan, 2015a,b,c, 2016; Azar & Zhu, 2015; Azar & Serrano, 2015a,b,c,d, 2016a,b, 2017; Boulkroune et al, 2016a,b; Ghoudelbourk et al., 2016; Meghni et al, 2017a,b,c; Azar et al., 2017a,b,c,d; Azar 2010a,b, 2012; Mekki et al., 2015; Vaidyanathan & Azar, 2015a,b,c,d, 2016a,b,c,d,e,f,g, 2017a,b,c; Zhu & Azar, 2015; Grassi et al., 2017; Ouannas et al., 2016a,b, 2017a,b,c,d,e,f,g,h,I,j; Singh et al., 2017; Vaidyanathan et al, 2015a,b,c; Wang et al., 2017; Soliman et al., 2017; Tolba et al., 2017).

Complete Chapter List

Search this Book: