Browsing by Author "Abdouni, Mohamed"

Now showing 1 - 3 of 3

ELECTROCHEMICAL CHROMIUM (VI) RECOVERY PROCESS BY CONDUCTING COMPOSITE, OLIVE POMACE/PANI
(ACADEMIA ROMÂNĂ, 2019) Babakhouya, Naouel; Abdouni, Mohamed; LOUHAB, Krim
We examined the use of a new conducting composite material which was prepared from olive pomace (OP) and polyaniline, developed and used for the fabrication of electrode, which was then used as substrate for the recovery of chromium hexavalent to an aqueous solution through electrical conductivity tests. We used the spectral analysis techniques such as FT-IR and X-ray diffraction (XRD) to characterize the material as well as Laser Particle Size and scanning electron microscopy (SEM) to show that the PANI was successfully attached to OP. We carried out electrosorption tests in acid medium within an electrochemical cell at a potential of +800 mV imposed and we compared the recovery with chemical adsorption at open circuit under the same conditions. The results demonstrated that the electrosorption of Cr (VI) is superior to the adsorption, which is due to the excellent electrical conductivity and mechanical properties of OP/PANI composite electrode. Through the electrosorption and electrodesorption we studied the possibility of regeneration of our electrode
Etude de l'adsorption et de la récupération électrochimique des métaux lourds par un matériau naturel conducteur
(2013) Abdouni, Mohamed
L'objectif de cette étude est l'adaptation d'un déchet naturel lignocellulosique " grignons d'olive " avec les techniques électrochimiques d'élimination des métaux lourds " chrome hexa-valent " dans l'eau. Pour atteindre ce but, on a prétraité et broyé les grignons d'olive, puis on a préparé des composites conducteurs de GO/PANI avec différentes techniques et différentes pourcentages en PANI et en GO. Une série de caractérisation par IRTF, Fluorescence X et la conductivité électrique, a été réalisé sur les GO, la PANI et les composites conducteurs, afin de déterminer les fonctions de surface et les composites de meilleurs propriétés. On fonction des résultats obtenues par ces caractérisations, on a choisi le composite qui entre dans la fabrication de l'électrode de travail. Finalement, dans une cellule électrochimique, on a réalisé des tests d'adsorption, et d'électrosorption dans des conditions expérimentales différentes
Interpreting NAS-Optimized Transformer Models for Remaining Useful Life Prediction Using Gradient Explainer
(Warszawa: Polskie Towarzystwo Informatyczne, 2025) Nekkaa, Messaouda; Abdouni, Mohamed; Boughaci, Dalila
Remaining Useful Life (RUL) estimation of complex machinery is critical for optimizing maintenance schedules and preventing unexpected failures in safety-critical systems. While Transformer architecture has recently achieved state-of-the-art performance on RUL benchmarks, their design often relies on expert tuning or costly Neural Architecture Search (NAS), and their predictions remain opaque to end users. In this work, we integrate a Transformer whose hyperparameters were discovered via evolutionary NAS with a gradient-based explainability method to deliver both high accuracy and transparent, perprediction insights. Specifically, we adapt the Gradient Explainer algorithm to produce global and local importance scores for each sensor in the C-MAPSS FD001 turbofan dataset. Our analysis shows that the sensors identified as most influential, such as key temperature and pressure measurements, match domain-expert expectations. By illuminating the int ernal decision process of a complex, NAS-derived model, this study paves the way for trustworthy adoption of advanced deep-learning prognostics in industrial settings.