ABDELHAFID Benyounes

ABDELLI Ahmed A.djaouad , ABBASSI Nadir

Système automatique pour la traduction de la langue des signes arabe algérienne

Khaireeddine Boudras

Application des techniques d'apprentissage automatique pour la detection et la classification des dèfauts de roulment dans les machines asynchrones

MOUSSAI Saber , SALEM Chaima

Diagnostic Des Défauts D’une Turbine A Gaz Basé Sur Des Techniques D’apprentissage Automatique

Somia Neguez , Manal Touirat

Power Management of Hybrid Fuel Cell System

ISSAME, MAHDJOUBI

Object Detection For Quadrotor Using Deep Learning

Dahoum Mehdi Abdessamad , Korichi Nabil Moustafa

Approches De L’intelligence Artificielle Pour La Commande Robuste Des Drones De Type Quadrotor

Ahmed keroucha , Youcef benhamodouche

Prédiction of cément fineness using Machine learning approaches

SEDDIKI Ridha , DAHRAOUI Nadjib

Détection des défauts dans un système industriel complexe utilisant la logique floue

Nouaoui tahar , Herizi kabes eddine

fuzzy modeling of the takagi-sugono type with to different techniques of clustring

Mustapha ZEGAIT , Alaa Eddine CHEBBI

Fuzzy Backstepping Control of a Quadrotor Unmanned Aerial Vehicle

BENKHIRA Med Cherif , BENHAMIDA Med Yazid

Automatisation d’un systéme de démarage du-rebouilleur de glycol par un API S7-300

Omane M.Mossaab , Benaoun Chaima

Commande par Backstepping pour la Stabilisation d‘Attitude d'un UAV de type Quadrotor

A Peak-Centric Approach to Bearing Fault Diagnosis Using Progressive Moving Transform and 2D- Convolutional Neural Network

Citation

ABDELHAFID Benyounes , , (2025-12-27), A Peak-Centric Approach to Bearing Fault Diagnosis Using Progressive Moving Transform and 2D- Convolutional Neural Network, International Journal of Robotics and Control Systems, Vol:5, Issue:27752658, pages:3284-3299, International Journal of Robotics and Control Systems

Thin-film planar heterojunction perovskite solar cells have emerged as promising candidates for next-generation photovoltaic technologies due to their low fabrication cost and high power conversion efficiency (PCE). Among the various materials explored, perovskite (CH3NH3PbI3) based solar cell considering n-i-p structure, stands out as a highly efficient absorber owing to their favorable optoelectronic properties, including high crystallinity, superior carrier mobility, and long diffusion lengths. Despite these advantages, the highest reported PCE for such cells remains at 24.3% (as of 2024). In this work, we present a novel thin-film perovskite solar cell design incorporating hybrid material interfaces and a one-dimensional photonic crystal at the device’s rear side to enhance photon recycling and reduce carrier recombination. Numerical simulations are performed using the Rigorous Coupled Wave Analysis (RCWA) method via the SYNOPSYS RSoft CAD tool, with layer thicknesses optimized using the MOST scanning and optimization module. The proposed architecture achieves a PCE of 22.5% with a fill factor of 89.3% under AM 1.5 solar conditions and a total device thickness of approximately 2.5 um. These results highlight the potential of the proposed design to surpass the 20% efficiency benchmark and offer a competitive alternative to conventional crystalline silicon photovoltaics.

Citation

Moufdi Hadjab , Mounir BOURAS , Salah KHENNOUF , ABDELHAFID Benyounes , , (2025-12-15), Improve Efficiency of Perovskite-Based Solar Cell by Photon Recycling, Boletim da Sociedade Paranaense de Matemática, Vol:43, Issue:7, pages:1-10, Sociedade Brasileira de Matematica

Bearing fault diagnosis is critical for predictive maintenance in industrial machinery, yet many existing data-driven methods struggle to adapt to varying operational loads and often analyze entire vibration signals, which can dilute key fault indicators. To address this, we propose a novel peak-centric approach that focuses on diagnostically rich signal regions, combining the Progressive Moving Average Transform (PMAT) with a 2D Convolutional Neural Network (CNN) for enhanced classification. Our primary contribution is a novel methodology that leverages localized peak regions for fault diagnosis, integrating the recently developed PMAT signal transformation and validating its generalization to mechanical systems to create highly discriminative 2D image representations from 1D vibration data. The method involves three key steps: extracting fixed-length signal fragments containing significant peaks, converting these fragments into 120×120 pixel images using the Left PMAT transform, and classifying the images into one of four health states using a custom 2D-CNN architecture. The model was rigorously evaluated on the CWRU dataset under a leave-one-load-out cross-validation scheme across four distinct load scenarios. It achieved exceptional performance, with macro-average F1-scores exceeding 99.83% in three of the four scenarios, specifically under loaded conditions (1-3 HP), and a top accuracy of 99.96%. A comparative analysis demonstrated that our PMAT-based method consistently outperformed a Continuous Wavelet Transform (CWT) baseline and other recent state-of-the-art models under these loaded scenarios. In conclusion, the proposed PMAT and 2D-CNN framework provides a robust and highly accurate tool for bearing fault diagnosis, successfully demonstrating PMAT's cross-domain generalization capability while establishing a competitive benchmark for future research. Future work will explore a hybrid PMAT-CWT transformation to further improve performance under zero-load conditions.

Citation

Rabah Mokhtari , ABDELHAFID Benyounes , Imad Eddine Tibermacine, Abdelaziz Rabehi, Alfian Ma’arif, , (2025-12-07), A Peak-Centric Approach to Bearing Fault Diagnosis Using Progressive Moving Transform and 2D- Convolutional Neural Network, International Journal of Robotics and Control Systems, Vol:5, Issue:6, pages:15, Association for Scientific Computing Electronics and Engineering (ASCEE)

Real-Time Sensor Fault Tolerant Control of DC-DC Converters in DC Microgrids Using a Switching Unknown Input Observer

Citation

ABDELHAFID Benyounes , , (2025-05-29), Real-Time Sensor Fault Tolerant Control of DC-DC Converters in DC Microgrids Using a Switching Unknown Input Observer, IEEE Access (2025)., Vol:13, Issue:21693536, pages:95837 – 95850, IEEE

Decentralized active fault tolerant control of direct current microgrids under actuator and source disturbances using proportional integral unknown input observer

Citation

ABDELHAFID Benyounes , , (2025-02-24), Decentralized active fault tolerant control of direct current microgrids under actuator and source disturbances using proportional integral unknown input observer, Scientific Reports, Vol:15, Issue:14392, pages:1, nature

Sensor faults are common problems in an islanded DC Microgrid, which significantly compromise the performance and operational integrity of the Microgrid. Aiming to detect and isolate sensor faults in islanded DC Microgrids, this paper proposes a robust fault detection and isolation scheme for an islanded DC Microgrid with uncertainties. Therein, a model considering the converter uncertainties is established and utilized to design the observer. Then, a residual-based function is generated that utilizes the estimation error of the observers to detect and identify faults. Model uncertainties are minimized on the estimation error by incorporating an H∞ uncertainty attenuation in to the observer design. The sufficient condition for stability is derived and expressed as Linear Matrix inequality (LMI). Simulation using Matlab/Simscape results are presented validating the accurate fault detection and identification

Citation

ABDELHAFID Benyounes , ,(2024-12-18), Decentralized Sensor Fault Detection and Isolation Using Robust Observer for a DC Microgrid,The 1st International Conference on Applications and Technologies of Renewable Energy Systems (ICATRES2024),algeria

Wind turbines, as one of the fastest-growing renew- able energy technologies, require advanced fault detection and diagnostic methods to maintain cost-effective and reliable energy production. The field of fault detection includes model-based and data-driven approaches, with recent advancements emphasizing data-driven techniques that leverage machine learning for more robust performance. In this paper, we aim to apply the Minimal Learning Machine (MLM) for fault detection and isolation (FDI) in wind turbines. MLM is a supervised machine learning technique that relies on distance-based learning to predict outputs by approximating relationships in the input space. This ap- proach offers a simpler and computationally efficient alternative to traditional machine learning methods while still providing accurate fault detection capabilities. For the fault detection phase, we employ indices to identify anomalies, SPE index (Squared Prediction Error) for indicating potential sensor/ actuator faults in the system. Fault isolation is achieved through structured residuals, using the principle of reconstruction to pinpoint specific faults. Our application concerned the benchmark Wind Turbine Supervisory Control and Data Acquisition (SCADA) system, which provides a comprehensive set of variables to evaluate MLM’s performance in terms of fault prediction and isolation. Index Terms—wind turbines, supervisory control and data acquisition (SACADA), fault detection and isolation, Fault re- construction, machine learning

Citation

ABDELHAFID Benyounes , ,(2024-12-18), Fault Detection and Isolation of Wind Turbine using Minimal Learning Machine,The 1st International Conference on Applications and Technologies of Renewable Energy Systems (ICATRES2024),algeria

.

Citation

ABDELHAFIDBenyounes , ,(2024-12-02); Traveux pratique Systèmes Asservis Linéaires et Continus,university of m'sila,

This study presents a novel machine learning approach for predicting modal indices in silicon waveguides. Our methodology employs a deep neural network (DNN) architecture to establish a robust link between waveguide geometric characteristics and their corresponding effective refractive indices (neff) for both transverse electric (TE) and transverse magnetic (TM) modes. The DNN is trained on a comprehensive data set generated by precise finite differenceeigen mode (FDE) simulations. The input features include waveguide width, height, and operating wavelength, while the outputs consist of the fundamental TE and TM mode indices. We employ a dual training methodology and a dynamic learning rate to improve model convergence and g Our methodology demonstrates remarkable accuracy, achieving a mean absolute error of less than 10-4 for neff predictions a cross many geometries relevant to silicon photonics. Notably, post-training, our method can predict modal indices for arbitrary waveguide dimensions within milliseconds, achieving a speed improvement beyond 1000 times relative to conventional si We evaluate our model's effectiveness using experimental data and demonstrate its application in accelerated design space exploration for silicon photonic devices. Furthermore, we illustrate the application of this strategy to complex waveguide designs, including multi- layer and slot waveguides, thereby enabling the efficient optimization of advanced photonic integrated circuits.

Citation

ABDELHAFID Benyounes , ,(2024-10-31), Efficient Prediction of Modal Indices in Silicon Waveguides Using Machine Learning Techniques,4th International Conference on Nanomaterials and Applications nanoMAT2024, Tunisia, 2024,Tunisia

In recent years, significant advancements have been made in thin-film planar heterojunction solar cells, emerging as cost-effective photovoltaic devices with high power conversion efficiency. Among the materials utilized, organometal trihalide perovskite (CH3NH3PbI3) stands out as a promising absorber material. Its appeal lies in the affordability of organic-inorganic perovskite compounds, readily available in nature, ease of fabrication, and compatibility with large-scale processing at low temperatures [1-2]. In addition to its effective absorption in the ultraviolet range, this material exhibits captivating optoelectronic properties, including high crystallinity, elevated carrier mobility, and extensive carrier diffusion lengths. Despite these advantages, the highest reported power conversion efficiency for perovskite solar cells is currently at 26.1%, as of 2022 [3]. This study introduces a thin-film organometal trihalide perovskite solar cell featuring hybrid interfaces between carefully chosen materials. These selections are the result of an in-depth study aimed at minimizing recombination and optimizing performance. Furthermore, we enhance the absorption of the incident solar spectrum by incorporating a 1D photonic crystal at the cell's bottom, facilitating the photon recycling process. The proposed solar cell parameters are numerically computed using the rigorous coupled wave algorithm through the SYNOPSYS RSOFT CAD tool. The thickness of each layer in the structure is optimized using the MOST scanning and optimization module of the RSOFT CAD tool, achieving the highest power conversion efficiency at a minimal device thickness (approximately 2.5 μm). Remarkably, the power conversion efficiency achieved is 27.5%, with a fill factor of 87.4% at AM 1.5, showcasing great promise. This demonstrates the remarkable potential of the proposed design to achieve efficiencies exceeding 5%, positioning it as a competitive contender in the existing crystalline silicon photovoltaic market.

Citation

ABDELHAFID Benyounes , ,(2024-10-31), Improve efficiency of Perovskite-Based Solar Cell by photon recycling,4th International Conference on Nanomaterials and Applications nanoMAT2024, Tunisia, 2024,Tunisia

.

Citation

ABDELHAFID Benyounes , ,(2024-06-15), Control of a Variable Speed Wind Turbine,3rd International Conference on Frontiers in Academic Research,Turkey

.

Citation

ABDELHAFID Benyounes , ,(2024-05-16), A variable speed electric drive based on a permanent magnet synchronous motor (PMSM),3rd International Conference on Engineering, Natural and Social Sciences ICENSOS 2024,Turky

.

Citation

ABDELHAFID Benyounes , ,(2024-04-18), Vector Control of Induction Motor Using Type-1 Fuzzy Logic Controller,2nd International Conference on Scientific and Innovative Studies ICSIS 2024,Turkey

A Decision Tree Approach for Detecting and Classifying Rolling Element Bearing Faults in Asynchronous Machines

Citation

ABDELHAFID Benyounes , ,(2024-04-18), A Decision Tree Approach for Detecting and Classifying Rolling Element Bearing Faults in Asynchronous Machines,2nd International Conference on Scientific and Innovative Studies ICSIS 2024,Turkey

- This paper focuses on the identification and modeling of gas turbine dynamics, specifically those used in power generation plants. The approach utilizes experimental data and employs fuzzy reasoning systems. The resulting model serves the purpose of approximating nonlinear gas turbine systems and ensuring reliable system control. By incorporating uncertainties associated with human reasoning, such as fuzzy systems based on Takagi-Sugeno reasoning, it is possible to achieve highly reliable control systems. The primary goal of this paper is to increase the effective monitoring system by employing nonlinear identification techniques, namely fuzzy systems and neuro-fuzzy systems, based on real-time on-site experimental data. Additionally, the proposed identification approaches are evaluated through a comparative study, where the results obtained using the Nonlinear Autoregressive Exogenous Neural Networks (NARX-NN) modeling technique are compared with those obtained using the Adaptive Inference System combined with the techniques of Neuro-Fuzzy renowned ANFIS concept. The obtained investigation results further facilitate the comprehension and analysis of the nonlinearities present in these complex systems, ultimately aiding in the prediction of their dynamic behavior

Citation

ABDELHAFID Benyounes , , (2023-06-01), A Comparative Modeling Study of Gas Turbine Using Adaptive Neural Network, Nonlinear Autoregressive Exogenous, and Fuzzy Logic Approaches for Modeling and Control, INTERNATIONAL JOURNAL OF SMART GRID, Vol:7, Issue:2, pages:90-102, INTERNATIONAL JOURNAL OF SMART GRID

Abstract—In that work, a type of an unmanned aerial vehicle (UAV) called quadrotor with an object detection system is the subject that we will talk about. The main objectives of our work is the detection of chosen objects from the quadrotor. For that, there are two parts presented, the first one, a detailed description of the mathematical effects that applied to the structure of our system and how we implemented our system with showing all the parts, and we used the PID controller to stabilize the system. In the second part, we will talk about artificial intelligence generally and deep learning specifically and we will show how exactly the detection happen using the right technics and algorithms with Yolov5 and which version we will use. Finally we will make a real test with the real time showing our prototype working in the field.

Citation

ABDELHAFID Benyounes , ,(2022), Real Time Object Detection With Drone Using Deep Learning Algorithm,the 2022 International Conference of advanced Technology in Electronic and Electrical Engineering (ICATEEE),Univ de M'sila algeria

The Principal Component Analysis (PCA) is one of the most known and used linear statistical methods for process monitoring. However, the PCA algorithm is not designed to handle the uncertainty of the sensor measurements that is represented by an interval type data. Including uncertainty of the sensors measurements in the analysis requires extending the PCA methodology to the Symbolic Data Analysis (SDA). The SDA refers to a paradigm where statistical units are described by interval-valued variables. In this regard, Symbolic Principal Component Analysis (SPCA), particularly Midpoints-Radii PCA (MRPCA) technique, is investigated for modeling and diagnosis of uncertain data. The aim of the present paper is to propose an extended version of the linear SPCA technique, based on midpoints and radii, to the nonlinear case of kernel PCA method (MR-KPCA). The basic idea is to construct a robust KPCA model from midpoints and radii of the nonlinear uncertain process data. Then, the robust KPCA model is used for diagnosis (FDI) purpose. In fact, the FDI decisions are improved by taking in to account the uncertainties on the nonlinear data. The MR-KPCA algorithm is applied for sensor fault detection and isolation of an automatic weather station. The results of applying this algorithm show its feasibility and advantageous performances.

Citation

ABDELHAFID Benyounes , , (2018), Diagnosis of uncertain nonlinear systems using interval kernel principal components analysis: Application to a weather station, ISA Transactions, Vol:83, Issue:, pages:126-141, elsevier

The use of gas turbines is widespread in several industries such as; hydrocarbons, aerospace, power generation. However, despite to their many advantages, they are subject to multiple exploitation problem that need to be solved. Indeed, the purpose of the present paper is to develop mathematical models of this industrial system using an adaptive fuzzy neural network inference system. Where the knowledge variables in this complex system are determined from the real time input/output data measurements collected from the plant of the examined gas turbine. It is obvious that the advantage of the neuro-fuzzy modeling is to obtain robust model, which enable a decomposition of a complex system into a set of linear subsystems. On the other side, by focusing on the membership functions for residual generator to get consistent settings based on the used data structure classification and selection, where the main goal is to obtain a robust system information to ensure the supervision of the examined gas turbine.

Citation

ABDELHAFID Benyounes , , (2017), Gas turbine modeling using adaptive fuzzy neural network approach based on measured data classification, Mathematics-in-Industry Case Studies, Vol:7, Issue:1, pages:4-18, Springer International Publishing

FUZZY MODELING AND SIMULATION OF GAS TURBINE USING FUZZY CLUSTERING ALGORITHM

Citation

ABDELHAFID Benyounes , ,(2017), FUZZY MODELING AND SIMULATION OF GAS TURBINE USING FUZZY CLUSTERING ALGORITHM,SIXTH INTERNATIONAL SCIENTIFIC CONFERENCE “ENGINEERING, TECHNOLOGIES AND SYSTEMS” TECHSYS 2017,SOFIA, PLOVDIV BRANCH, Bulgaria

This book presents current research in the area of gas turbines for different applications. It is a highly useful book providing a variety of topics ranging from basic understanding about the materials and coatings selection, designing and modeling of gas turbines to advanced technologies for their ever increasing efficiency, which is the need of the hour for modern gas turbine industries

Citation

ABDELHAFIDBenyounes , ,(2017); Encyclopaedia of Gas Turbines: Materials, Modeling and Performance,,Auris Reference Limited

Traditional techniques for addressing vibration in gas turbines are unable to adapt to complex modern operating environments. Uncontrolled dynamic vibration can lead to premature aging of turbine components, or unacceptable noise and vibration. To achieve operational efficiency in gas turbine control, this article proposes new methods based on artificial intelligence tools and applies them to Sonatrach’s gas compression station Medjebara SC3 in Djelfa, Algeria, on the Hassi R’mel-Bejaia (GG1) pipeline, part of a 1,400-km natural gas line connecting Algeria to Europe. This article proposes using fuzzy-logic techniques to examine a gas turbine system that includes several interacting components, the failure of which could lead to both lost revenues and lost lives.

Citation

ABDELHAFID Benyounes , , (2016), Fuzzy logic addresses turbine vibration on Algerian gas line, Oil & Gas Journal, Vol:114, Issue:1, pages:22-28, PennWell Publishing Co. Energy Group, Tulsa, USA

Automation production systems evolution makes the failures diagnosing essential for industrial development. The work developed in this thesis is a contribution to the study of methods of control to faults tolerant, for the detection and localization of defects based on fuzzy models. This work aims to identify and model the dynamics of a gas turbine, used in industrial plants, from experimental data to approximate variable of this nonlinear system, by integrating the inaccuracies of human reasoning as rules and linguistic variables. This is to achieve an effective implementation of this system based on the use of models obtained in their strategy of fault tolerant control. The obtained results are satisfactory and give justification to further the applicability of fuzzy control fault tolerant approach in industry, especially for problems of diagnosis and monitoring of complex processes.

Citation

ABDELHAFIDBenyounes , ,(2016); Commande floue tolérante aux défauts appliquée à la supervision des vibrations dans les turbines à gaz: Application sur une turbine TITAN 130,Université de Djelfa,

The development of reliable mathematical models for nonlinear systems has been a primary topic in several industrial applications. This work proposes to examine the application of fuzzy logic to represent the control parameters of a gas turbine based on the fuzzy clustering method using Gustafson–Kessel algorithms. The results obtained from data classification of construction with associated models indicate applications in modeling the examined system.

Citation

ABDELHAFID Benyounes , , (2016), Gas Turbine Modeling Based on Fuzzy Clustering Algorithm Using Experimental Data, Applied Artificial Intelligence, Vol:30, Issue:1, pages:29-51, Taylor and francis

Nowadays, gas turbines are one of the major parts of Modern industry. They have played very important role in aeronautical industry, power generation and main mechanical drivers for large pumps and compressors. This study addressed the modeling and the simulation of the Industrial Gas Turbine Solar TITAN 130 with two shafts, located in the gas injection station of Djelfa in Algeria. The used method for modeling of this gas turbine is based on adaptive neuro-fuzzy inference system (ANFIS) with the use of fuzzy c-mean clustering (FCM) algorithm.

Citation

ABDELHAFID Benyounes , ,(2015), Adaptive neuro-Fuzzy modeling of an industrial Gas turbine Based a exprimental data,International Conference on Automatics and Mechatronics CIAM’2015,Oran ,Algérie

Today, gas turbines are one of the major parts of modern industry. They have played very imported in aeronautical industry, power generation, and main mechanical drivers for large pumps and compressors, In this paper a proportional-integral (PI) control design of an industrial gas turbine based on fuzzy modeling is constructed, this work addressed the major problem of the gas turbine, the system modelling, a fuzzy modeling is used to build the system model, a PI speed control is proposed, a comparison with the mathematical model proposed by Rowen is discussed, the simulations results show that the proposed fuzzy model is reliable and can be used for gas turbine control and diagnosis.

Citation

ABDELHAFID Benyounes , ,(2015), Control of an industrial gas turbine based on fuzzy model,16th IFAC Conference on Technology, Culture and International Stability,Sozopol, Bulgaria

The development of mathematical models for industrial systems is an important topic in many disciplines of science and engineering. The implementation of the laws governing equations such industrial systems, leads to a model of knowledge too complex and their use in control is very delicate. This work, present fuzzy Takagi Sugeno models identification developed to an examined gas turbine, using experimental data in real time. The obtained results show that the proposed technique is efficient to approximate the model of the examined gas turbine.

Citation

ABDELHAFID Benyounes , ,(2015), Takagi Sugeno models identification based on fuzzy data construction: Gas turbine investigation,International Conference on Applied Automation and Industrial Diagnostics (ICAAID 2015),,Djelfa ,Algérie

This paper presents a decentralized control strategy for the stabilization of a Quadrotor helicopter attitude, based on the combining of the fuzzy logic control and sliding mode control (SMC). The main purpose of this work is to reduce the chattering phenomenon. To achieve our purpose we have used a fuzzy logic control to generate the discontinue part of control signal in SMC, the results of our simulations indicate that the control performance of the stabilization of the Quadrotor are satisfactory and the proposed fuzzy sliding mode control (FSMC) can achieve favorable performance.

Citation

ABDELHAFID Benyounes , ,(2015), Decentralized Fuzzy Sliding Mode Control With Chattering Elimination for the Stabilisation of a Quadrotor Helicopter Attitude,The 1st International Conference on Applied Automation and Industrial Diagnostics (ICAAID 2015),,Djelfa ,Algérie

Fuzzy modeling and control of an industrial Gas turbine

Citation

ABDELHAFID Benyounes , ,(2015), Fuzzy modeling and control of an industrial Gas turbine,9ème Conférence sur le Génie Electrique,Alger-Algeira

Fuzzy identification and modeling is one of the best approaches for the representation of complex systems. In this article we use the Takagi-Sugeno fuzzy model for some class of nonlinear system, in order to use this proposed approach in various industrial applications. The validation of the proposed model was tested by the clustering technique, based on Gustafson-Kessel algorithm, to a multivariable industrial system. . Key words: Fuzzy modeling, Takagi-Sugeno fuzzy model, Gustafson-Kessel algorithm, complex systems, industrial applications, multivariable industrial system.

Citation

ABDELHAFID Benyounes , , (2013), Fuzzy modeling of Multiple-Input Multiple-Output systems using Takagi-Sugeno models based on Gustafson-Kessel clustering, The International Journal on Advanced Electrical Engineering, Vol:1, Issue:3, pages:150-160, The International Journal on Advanced Electrical Engineering ISSN:2335-1209