Claim Missing Document
Check
Articles

Found 5 Documents
Search

Parametric Analysis of Climate Factors for Monthly Weather Prediction in Ghardaïa District Using Machine Learning-Based Approach: ANN-MLPs Dahmani, Abdennasser; Ammi, Yamina; Ikram, Kouidri; Kherrour, Sofiane; Hanini, Salah; Al-Sabur, Raheem; Laidi, Maamar; Ma’arif, Alfian; Sharkawy, Abdel-Nasser
International Journal of Robotics and Control Systems Vol 5, No 1 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i1.1651

Abstract

In the rapidly developing field of smart cities, accurately predicting weather conditions plays a vital role in various sectors, including industry, tourism, agriculture, social planning, architecture, and economic development. Unfortunately, the instruments used (such as pyranometers, barometers, and thermometers) often suffer from low accuracy, high computational costs, and a lack of robustness. This limitation affects the reliability of weather predictions and their application across these critical areas. This study proposes artificial neural network-multilayer perceptrons (ANN-MLPs). A dataset of 480 data points was used, with 80% allocated for the training phase, 10% for the validation phase, and 10% for the testing phase. The best results were obtained with the structure 6-17-1 (6 inputs, 17 hidden neurons, and 1 output neuron) to predict weather condition data in the Ghardaïa district. Weather conditions parameters include air temperature, relative humidity, wind speed, and cumulative precipitation. Results showed that the most relevant input factors are, in order of importance: earth-sun distance (DT-S) with a relative importance (RI) of 31.10%, factor conversion (d) with an RI of 26.05%, and solar radiation (SR) with an RI of 16.26%. The contribution of the elevation of the sun (HI) has an RI of 13.29%. The optimal configuration includes seventeen neurons in the hidden layer with a logistic sigmoid activation function and a Levenberg–Marquardt learning algorithm, resulting in a root mean square error (RMSE) of 3.3043% and a correlation coefficient (R) of 0.9683. The proposed model can predict both short- and long-term climate factors such as solar radiation, air temperature, and wind energy in areas with similar conditions.
Modeling the Structural Dynamics of Carbon Fiber Composites for Robotic Systems Under Sinusoidal Load Al-Sabur, Raheem; Ameen, Yahya Muhammed; Khalaf, Hassanein I.; Mishra, Akshansh; Sharkawy, Abdel-Nasser
International Journal of Robotics and Control Systems Vol 5, No 1 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i1.1693

Abstract

The demand for robotic systems employing composite materials is steadily improving due to their high bending stiffness, favorable strength-to-weight ratio, and durability under dynamic loading. It is still challenging to guarantee dynamic stability and precise frequency response in composite robotic components. This study addresses these issues by conducting a simulation-based 3D bending analysis and frequency response modeling of carbon/epoxy and carbon/PPS composites under sinusoidal loading. The remarkable mechanical and thermal properties of carbon/epoxy and carbon/PPS composites, such as their high specific strength, stiffness, and excellent fatigue resistance, align well with the requirements of robotic systems. The model comparison involved analyzing three-dimensional bending stresses, displacements, and free vibration dynamics for both materials under a sinusoidal load applied to their inner surfaces. The sinusoidal load was selected to simulate periodic dynamic forces commonly encountered in robotic applications, such as oscillating arms, vibrating components, and cyclic loading during operation. The thick shell (S=4) of axial length (L=4S) and circumferential span (α=45°) comprises cross-ply laminate [90°/0°/90°] with supported boundary conditions. The transverse displacement of the carbon PPS composite cylindrical shell was 0.719 nm, which was lower than that of the carbon epoxy composite (0.746 nm). The same behavior was observed for the stress values. Conversely, the PPS composite cylindrical shell yielded a higher natural frequency. The obtained eigenvalues indicated a similar behavior when comparing the shape modes with a relative increase in their values in the carbon PPS composite.
A New Adaptive Flux-Oriented Control Framework for Induction Motors with Online Neural Network Training Bekhiti, Belkacem; Al-Sabur, Raheem; Sharkawy, Abdel-Nasser
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 3 (2025): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i3.13727

Abstract

Unlike conventional field oriented control methods, this paper presents a mathematically novel control strategy for induction motor drives, formulated using a two-loop nonlinear dynamic inversion (NDI) framework inspired by aeronautical control architectures. Sensorless operation is realized with a conventional rotor flux observer, while several additional enhancements are introduced to raise overall performance. In particular, a real time radial basis function (RBF) neural network is systematically embedded in a model reference adaptive system (MRAS), replacing the traditional PI adaptation loop with an online training mechanism that improves speed estimation accuracy under parameter variations and load disturbances. The single layer RBF network is trained by gradient descent and incorporated into the nonlinear observer without compromising closed loop stability. The complete controller was implemented on a 1.1 kW, 1430 rpm induction motor using a dSPACE DS1104 real time platform. Experimental results show clear superiority over classical FOC as well as DTSFC and DTRFC schemes, achieving the lowest measured flux ripple (0.002 Wb), minimal torque ripple (0.043 N·m), and the fastest torque response time (0.65 ms). The steady state speed error was reduced by 91 % (from 0.65 to 0.08 rad/s), settling times remained below 60 ms, and both RMSE and ISE metrics decreased appreciably across all tested conditions. Although the proposed design incurs moderate computational overhead, it is fully compatible with real time execution. Future work will examine scalability to high power drives, improved resilience to temperature induced parameter drift, and adaptation of the NDI based framework to permanent magnet machines.
Temperature-Controlled Process for Recycled Waste Tire Polymer-Polymer Composites: An Innovative and Sustainable Solution for Marine Fender Applications Zaibel, Ali Habel; Almtori, Safaa A. S.; Al-Sabur, Raheem; Sharkawy, Abdel-Nasser
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 3 (2025): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i3.13813

Abstract

Marine fender prototypes play a critical role in protecting the ship and the berthing infrastructure from damage during docking. Recycling waste polymers, such as waste tires, into composite materials for marine fenders, can contribute to environmental sustainability and resource conservation. In marine Fender applications, compression testing often plays a crucial role; we should also test factors such as elasticity, stiffness, and hardness. In this study, pressure and hardness were selected, and Young's modulus was calculated for two types of composite materials: one manufactured from waste tires and high-density polyethylene (HDPE) and the other from waste tires and room-temperature vulcanized (RTV) silicone both in varying proportions. These types of materials were produced using a press machine equipped with a PID controller, which enables the adjustment of the temperature to a desired value, thereby achieving the best results. Prototypes containing 85% waste tire with 15% HDPE and 50% waste tire with 50% RTV silicone showed superior energy absorption and durability for marine fender applications. Despite achieving satisfactory hardness and hardness values, the waste tire and RTV silicone composite did not exceed those of the waste tire and HDPE composites, which had Young's modulus and Shore hardness values of 1.74 MPa and 56.6, respectively. The compression test showed that the waste tire and RTV silicone composites achieved higher values, surpassing 1990 kN. The findings provide a crucial foundation for utilizing waste composite materials in marine fender production.
Trends and Impact of the Viola-Jones Algorithm: A Bibliometric Analysis of Face Detection Research (2001-2024) Wijaya, Setiawan Ardi; Famuji, Tri Stiyo; Mu'min, Muhammad Amirul; Safitri, Yana; Tristanti, Novi; Dahmani, Abdennasser; Driss, Zied; Sharkawy, Abdel-Nasser; Al-Sabur, Raheem
Scientific Journal of Engineering Research Vol. 1 No. 1 (2025): January
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v1i1.2025.8

Abstract

The Viola-Jones algorithm remains a cornerstone in computer vision, particularly for object and face detection. This bibliometric study provides a comprehensive analysis of the algorithm’s academic impact and research trends, encompassing publication patterns, citation metrics, influential authors, and co-occurrence of keywords. The findings indicate a significant rise in research outputs and citations between 2016 and 2020, reflecting the algorithm's sustained relevance and application in various domains. Network visualization maps further reveal the algorithm's integration with diverse fields, including machine learning, image processing, and neural networks, emphasizing its versatility and adaptability to emerging technological challenges. Key research contributions include advancements in hybrid approaches, combining the Viola-Jones framework with techniques such as convolutional neural networks and HOG-SVM for improved detection accuracy. However, limitations such as computational inefficiency and sensitivity to environmental factors persist, presenting opportunities for innovation. This study concludes by highlighting future research directions, such as integrating deep learning and edge computing to enhance algorithmic performance in real-time and complex scenarios. This study provides a valuable reference for researchers and practitioners aiming to extend the Viola-Jones algorithm’s capabilities and applications by consolidating existing knowledge and identifying research gaps.