Browsing by Author "Rabiai, Zakaria"

Now showing 1 - 3 of 3

Design and implementation of speed and torque controller for DC motor
(2018) Rabiai, Zakaria; Dahimene, A. (Supervisor)
The purpose of this project is to implement an end-to-end automatic speech recognition system using recurrent neural networks, the Arabic language which ranks as the fifth most spoken language in the world has been chosen as the main language of the system. The Arabic language has been alienated from such type of projects due to its complexity, uniqueness and lack of free appropriate corpuses, but with new emerging algorithms in the domain of speech recognition such as the connectionist temporal classification, it is becoming more accessible to use unsegmented corpuses in the aim of building performant automatic speech recognition systems. The development of the project
Fuzzy logic enhanced control for a single-stage grid-tied photovoltaic system with shunt active filtering capability
(Wiley, 2021) Ayachi Amor, Yacine; Hamoudi, Farid; Kheldoun, Aissa; Didier, Gaëtan; Rabiai, Zakaria
In this paper, a three-phase single-stage grid-connected photovoltaic (PV) system with active power filtering capability by means of a three-level T-type inverter is presented. The system is intended to fulfill many functions: harmonic mitigation, unity power factor operation, maximum power extraction from PV source, and so on. For the proposed system to achieve these tasks with a good dynamic performance, a new control strategy based on the fuzzy logic controller is developed. Fuzzy control has three main stages and each one requires many settings or selection of parameters. A new approach of setting the scaling factors which considerably affect the system's response is proposed. Furthermore, a methodology to properly set the fuzzy rules is suggested. The electrical power chain of the system comprises a farm of a PV source, three-level T-type inverter space vector pulse width modulation controlled, inductor filter, non-linear load, and the utility grid. To evaluate the performance of the proposed control, a processor-in-the-loop is performed as a hardware verification of the inverter control algorithm using a low-cost STM32F4 discovery board, while the power circuit plant is modeled in the host computer using Matlab/Simulink. The obtained results are very satisfactory and confirm the role of each component, especially in terms of maximum power tracking, power quality, unity power factor operation, and control robustness
Multi-agent system for voltage regulation in smart grid
(Springer, 2020) Belaidi, Hadjira; Bentarzi, Hamid; Rabiai, Zakaria; Abdelmoumene, Abdelkader
In this research work, a new approach of decentralized energy management for smart grid is proposed to solve the problem of distributed voltage regulation. Where, micro-grids and aggregators are used as smart agents that can communicate with each other to share information, distribute energy and control their own energy consummation. Aggregators make the link between flexible resources. Smart-agents are an emerging technology for decentralized computation and data storage, secured by a combination of cryptographic signatures and a distributed consensus mechanism. So, two types of agents: energy Generation AGent (GAG) and Bus Agent (BAG) are used to regulate the voltage levels by injecting more power at some buses using the renewable energy sources. The interaction between the two types of agents is based on communication and exchange of information about the parameters and the state of the power grid. For testing this approach, a developed tester by our laboratory has been used that gives a good result