Electrical and Electronic Engineering, Computer Engineering, Artificial Intelligence, Control and Optimization
FUTURE PROJECTS
High-Voltage Techniques for Efficient Cleaning and Performance Enhancement of Solar Panels
Applications Invited
High-Voltage Techniques for Efficient Oil–Water Separation in Crude Petroleum Processing
Applications Invited
13
Scopus Publications
Scopus Publications
Development of a NARX neural network for a tribo-aero-electrostatic separator with rotating disk electrodes Z. Ayache, O. Dahou Electrical Engineering and Electromechanics, 2026 Introduction. The exponential growth of waste electrical and electronic equipment (WEEE) requires efficient strategies for plastic waste management. Plastics, a major fraction of WEEE, represent both an environmental challenge due to low biodegradability and a valuable source of secondary raw materials. Problem. Tribo-aero-electrostatic separators with rotating disk electrodes offer a promising solution for fine plastic separation. However, their performance depends on multiple, nonlinear, and time-varying factors such as disk speed, voltage, and particle properties. These complex interactions make analytical modeling and stable process control difficult, limiting industrial implementation. The goal of this work is to develop a reliable dynamic model based on NARX neural networks capable of predicting the real-time evolution of key process variables such as recovered mass and particle charge. Methodology. The proposed NARX neural network learns temporal nonlinear relationships directly from experimental data, avoiding the need for explicit physical equations. Experiments were conducted on a synthetic 50:50 mixture of Acrylonitrile Butadiene Styrene (ABS) and Polystyrene (PS) particles (500-1000 μm) to assess model performance under varying disk speeds, voltages, and air flow rates. Results. The developed model accurately predicts the recovered mass and acquired charge of both ABS and PS over a wide range of operating conditions. The predictions show strong agreement with experimental measurements, maintaining low error levels even at parameter extremes. Scientific novelty. This work represents the first application of NARX neural networks to model the dynamic behavior of a two-rotating-disk tribo-aero-electrostatic separator. The approach captures essential time-dependent interactions that conventional static or analytical models fail to describe. Practical value. The NARX model exhibits high predictive accuracy and robustness across an extended operating domain (4–20 kV, 15–60 rpm, 7–9 m3/h), with errors limited to the 10–3 g and 10–3 µC ranges. These characteristics demonstrate its potential for real-time intelligent control and adaptive optimization of electrostatic separation processes in plastic waste recycling. References 39, tables 3, figures 9.
Experimental Study of a Low-Pressure Glow Discharge Characteristics in a Thin Film Deposition Plasma Reactor Bekkara Mohammed Fethi, Dahou Omar, Houari Ahmed Toufik, Benmimoun Youcef, Belaribi Imene, Oualhaci Noureddine, Bouhediba Abdelkrim, Lagua Solaire Icaee 2024 International Conference on Advanced Electrical Engineering 2024, 2024 The work carried out in this paper falls within the framework of fundamental research on electrical discharges. Thus, the work of this paper is focused on the study of the electrical characteristics of electroluminescent discharges in a plasma reactor intended for the deposition of thin metallic film. The discharges are established under low pressure in a rare gas, which is Argon. The experimental study showed that the decrease in the inter-electrode distance or the gas pressure allows to change the discharge regime towards the regime of the abnormal electroluminescent discharge, which is more energetic and suitable for the deposition of the thin film. In addition, the analysis of the experimental breakdown voltage curves in the reactor revealed that Paschen's law is not verified and requires further studies on the effect of the shape and size of the electrodes as well as on the type of electrode materials used in the reactor.
Modeling the performance of an Electrodynamic screen (EDS) with artificial intelligence techniques Toufik Houari Przeglad Elektrotechniczny, 2023 Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.
Optimal Operation of a Plate-Type Corona-Electrostatic Separator for the Recovery of Metals and Plastics from Granular Wastes Thami Zeghloul, Seddik Touhami, Gontran Richard, Mohamed Miloudi, Omar Dahou, Lucian Dascalescu IEEE Transactions on Industry Applications, 2016 Plate-type electrostatic separators are commonly employed for the selective sorting of conductive and nonconductive granular materials. Unfortunately, the purity of the conductive products is often compromised by the fact that the trajectories of the nonconductive granules cannot be controlled. The aim of the present work is to validate a relative simple solution to this problem: subjecting the granules to a corona discharge during their sliding down the plate electrode. This discharge does not affect the conductive granules but charges the nonconductive ones, so that the electric force would tend to pin them to the surface of the grounded electrode. In this way, the friction forces between the granules and the plate increase and the inertia forces decrease. Design of experiments methodology is employed to identify the optimum high-voltage, relative position of the electrodes, and configuration of the collector. The conclusions of this study served at the optimum design of an industrial corona-assisted plate-type electrostatic separator for the recycling of metals and plastics from granular electric cable wastes.
Corona-assisted plate-type electrostatic separation process for granular plastic wastes Thami Zeghloul Lucian Dascalescu, Seddik Touhami, Mohamed Miloudi, Omar Dahou, Gontran Richard IEEE Industry Application Society 51st Annual Meeting IAS 2015 Conference Record, 2015 Plate-type electrostatic separators are commonly employed for the selective sorting of conductive and non-conductive granular materials. Unfortunately, the purity of the conductive products is often compromised by the fact that the trajectories of the non-conductive granules cannot be controlled. The aim of the present work is to validate a relative simple solution to this problem: subjecting the granules to a corona discharge during their sliding down the plate electrode. This discharge does not affect the conductive granules but charges the non-conductive ones, so that the electric force would tend to pin them to the surface of the grounded electrode. In this way, the friction forces between the granules and the plate increase and the inertia forces decrease. Design of experiments methodology is employed to identify the optimum high-voltage, relative position of the electrodes, and configuration of the collector. The conclusions of this study served at the optimum design of an industrial corona-assisted plate-type electrostatic separator for the recycling of metals and plastics from granular electric cable wastes.
Modeling and optimization of a roll-type electrostatic separation process using artificial neural networks Seddik Touhami, Karim Medles, Omar Dahou, Amar Tilmatine, Abdelber Bendaoud, Lucian Dascalescu IEEE Transactions on Industry Applications, 2013 The aim of this paper is the development of a procedure for the optimization of electrostatic separation processes using artificial neural networks (ANNs) in association with genetic algorithms. The objective was to maximize the insulation product, the control variables being the high voltage that supplies the electrode system and the rotation speed of the roll electrode. The ANN model is compared with that obtained using the classical experimental design methodology. The predicted optimum is confirmed by experiment.
Application of genetic algorithms to the optimization of a roll-type electrostatic separation process Omar Dahou, Karim Medles, Seddik Touhami, Mohamed Fodil Boukhoulda, Amar Tilmatine, Lucian Dascalescu IEEE Transactions on Industry Applications, 2011 The aim of this work is the development of a procedure for optimal control of electrostatic separation processes for the recycling industry using a genetic algorithm. The target is to maximize the conductor product, with the control variables being the high voltage that supplies the electrode system of the roll-type corona-electrostatic separator and the inclination of the splitter between the two compartments in which are collected the conductor product and the middling. The effectiveness of the procedure is tested against a situation of dysfunction that can occur in industrial practice: a variation of the speed of the rotating roll electrode.