Article Per Year (5 Year)
p-Index From 2021 - 2026
1.518
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Journal of Robotics and Control (JRC) International Journal of Robotics and Control Systems Automotive Experiences
Ghazaly, Nouby M.
Unknown Affiliation
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Materials Science & Nanotechnology Mechanical Engineering

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : International Journal of Robotics and Control Systems

 1 
Comparative Study of ANN and SVM Model Network Performance for Predicting Brake Power in SI Engines Using E15 Fuel Hofny, Mohamed S.; Ghazaly, Nouby M.; Shmroukh, Ahmed N.; Abouelsoud, Mostafa
International Journal of Robotics and Control Systems Vol 4, No 3 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i3.1429

Abstract

Currently, artificial neural networks (ANNs) and support vector machines (SVMs) are the most common applications of machine learning approaches.  In this study, a comparative study of ANN and SVM is presented to evaluate the performance of each model in predicting the brake power (BP) of GX35-OHC 4-stroke, air-cooled, single cylinder gasoline engine with E15 (15% ethanol + 85% gasoline) fuel. Two models are compared based on experimental dataset that has single output (BP) and five inputs, engine speed (S), engine torque (T), intake air temperature (Tair), intake air flow (Qair), and fuel consumption (ṁ). The samples were split into three sets: Training set (70%), Validation set (15%), and the Test set (15%) based on 60 samples. The results are compared through different graphs such as target vs actual values, regression plots, histograms of prediction errors, residual plots, learning curves, and error distributions. The results showed that SVM model is indicated to have lower RMSE (0.0044) and higher EVS (0.9953), while ANN is shown to have lower value of MAPE (1.51%). These results have significant implications for the use of ANN and SVM models in real-world applications that need gradual comprehensibility and model generalization. In addition, work done with the models outlined above should try and test them in other engines and operating conditions to demonstrate the model’s and performance.
Using Active Filter Controlled by Imperialist Competitive Algorithm ICA for Harmonic Mitigation in Grid-Connected PV Systems Hadi, Husam Ali; Kassem, Abdallah; Amoud, Hassan; Nadweh, Safwan; Ghazaly, Nouby M.; Moubayed, Nazih
International Journal of Robotics and Control Systems Vol 4, No 2 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i2.1365

Abstract

Solar energy has been gaining momentum recently, with a focus on maximizing its investment potential due to its reputation as the most sustainable and efficient energy source. This shift towards solar power could potentially reduce the reliance on oil-based fuels in the future. As a result of the integration of photovoltaic (PV) energy sources into the grid, the reliability of power distribution and maintaining its quality in these systems has become increasingly important. The presence of non-linear loads in these grids causes distortion of both voltage and current waves on the grid side, so it is necessary to implement effective reduction techniques to reduce the distortions in these waves. The research contribution is TO introduce the integration of an active filter on the dc side of grid-connected PV systems, along with a control circuit for the filter switches. The control switches were operated using a Sinusoidal Pulse Width Modulation (SPWM) control scheme, while the controller parameters were tuned using the Imperialist Competitive Algorithm (ICA). The proposed system was simulated in the MATLAB/Simulink environment with variations in solar radiation and temperature. The simulation results demonstrated a reduction in the total harmonic distortion factor (THD) for voltage and current waveforms on the grid side, which are within the permissible limits. This confirms the effectiveness of the proposed filter and the efficiency of the control strategy and algorithm for parameter adjustment.
Two-Flexible-Link Manipulator Vibration Reduction Through Fuzzy-Based Position Faris, Waleed F.; Rabie, M.; Moaaz, Ahmad O.; Ghazaly, Nouby M.; Makrahy, Mostafa M.
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.v5i1.1669

Abstract

The increasing demand for robotic applications has emphasized the need for advanced control strategies, particularly for flexible manipulators with lightweight links. These manipulators offer advantages such as reduced energy consumption, increased payload capacity, and precise high-speed operation but face challenges due to oscillations and delays caused by their flexibility. This study evaluates the performance of Fuzzy Logic Control (FLC) and Linear Quadratic Regulator (LQR) techniques for a Quanser two-link flexible manipulator, using quantitative metrics to compare their effectiveness. The LQR controller was implemented using state-space modeling, with weighting matrices Q and R tuned to achieve minimal overshoot and fast settling times. The FLC system employed five triangular membership functions for inputs and outputs, covering normalized ranges of [-1, 1] for angular errors and [-2.75, 2.75] for error rates, with a heuristic rule base designed to optimize performance. Simulations were conducted under step input conditions at target angles of 30° and 60°, with performance evaluated using vibration amplitude, settling time, steady-state error, and overshoot. Quantitatively, the LQR controller reduced vibration amplitudes to 5 radians for a 30° input and achieved settling times of approximately 2 seconds. For the same conditions, the FLC system reduced vibrations further to 4 radians, though with slightly longer settling times of around 2.3 seconds. At a 60° input, LQR vibrations peaked at over 10 radians, while FLC maintained peak vibrations at approximately 4 radians. These results highlight the FLC’s superior vibration suppression, particularly at higher input angles, albeit with marginally slower response times. However, the study was limited to idealized simulation conditions and requires further experimental validation. This research underscores the trade-offs between LQR’s precision and FLC’s adaptability, emphasizing the importance of parameter tuning and system modeling in achieving optimal performance for flexible manipulators.
Co-Authors Abd - Elwahab, M. Rabie Abdulhameed, Ahmed N. Abdulhasan, Mahmood Jamal Abouelsoud, Mostafa Albaker, Baraa Munqith Amoud, Hassan Faris, Waleed F. Faris, Waleed Fekry Hadi, Husam Ali Hailan, Maryam Abdulhakeem Hofny, Mohamed S. Kassem, Abdallah Makrahy, Mostafa M. Moaaz, Ahmad O. Moubayed, Nazih Nadweh, Safwan Rabie, M. Shmroukh, Ahmed N.