Mohammed Adaika
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammed Adaika has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Abdelkader Mahmoudi
UDERZA Unit, Mechanical Department, Faculty of Technology, University of El Oued, 39000 El Oued, Algeria
2 shared publications - Mosbah Laouamer
University of ElOued
2 shared publications - Souhaib Remha
University of ElOued
2 shared publications - Abderazak Bennia
Department of Electromechanical Engineering, LPMRN Laboratory, Faculty of Sciences and Technology, University Mohamed El Bachir El Ibrahimi of Bordj Bou Arreridj, Bordj Bou Arrridj, Algeria
1 shared publication - Abderrahim Reffas
LPMRN Laboratory, Department of Electromechanical Engineering, Faculty of Sciences and Technology, University Mohamed El Bachir El Ibrahimi of Bordj Bou Arreridj, El-Anasser, Algeria
1 shared publication - Abderrahmane Beroual
Ecole Centrale de Lyon, Ampere CNRS UMR 5005, University of Lyon, Ecully, France
1 shared publication
Latest Publications
- Open Access
- 17 March 2026
- Published by Polskie Towarzystwo Diagnostyki Technicznej in Diagnostyka
- Vol. 27 (1) , 1-11
A residual current-based indicator for early detection of stator winding faults in synchronous reluctance machines
In the last decades, the on-line detection of incipient short-circuit faults for electrical machines has been a major challenge, particularly in closed-loop conditions. It is found in the literature that the 2nd harmonics in both dq-axis currents were used for fault detection, and the main...
- 17 March 2026
- Published by Polskie Towarzystwo Diagnostyki Technicznej in Diagnostyka
- Vol. 27 (1) , 1-11
Open AccessA residual current-based indicator for early detection of stator winding faults in synchronous reluctance machines
In the last decades, the on-line detection of incipient short-circuit faults for electrical machines has been a major challenge, particularly in closed-loop conditions. It is found in the literature that the 2nd harmonics in both dq-axis currents were used for fault detection, and the main...
- Open Access
- 10 December 2025
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 13 (4) , 712-721
Comparative Deep Learning for RGB-Based PV Surface Fault Classification Using ResNet50 and EfficientNetB0 with Real-Time Deployment
Photovoltaic (PV) systems are increasingly vital to global energy transitions but remain vulnerable to surface anomalies such as dust, snow, bird droppings, and physical or electrical damage—that significantly reduce power yield and long-term reliability. Manual inspection is inefficient for large-scale solar farms, motivating the development of intelligent and automated fault detection systems. This study introduces a reproducible comparative deep-learning framework that systematically benchmarks four convolutional neural network (CNN) architectures ResNet50, EfficientNetB0, MobileNetV3Small, and DenseNet121 under identical preprocessing, training, and validation settings. The framework integrates runtime efficiency analysis, five-fold cross-validation, and a real-time GUI-based deployment interface, bridging the gap between academic benchmarking and field-level implementation. A six-class labeled dataset of 1,574 RGB images was expanded through extensive data augmentation (rotation, flipping, brightness adjustment, and Gaussian noise perturbation) to simulate diverse real-world conditions. Among the four tested models, DenseNet121 achieved the highest macro-averaged F1-score (≈ 0.96), followed by ResNet50 (0.93), EfficientNetB0 (0.92), and MobileNetV3Small (0.92), highlighting clear accuracy–efficiency trade-offs across architectures. The novelty of this work lies in its multi-model benchmarking design and transparent methodology, providing a standardized and reproducible reference for future PV image-based diagnostics. Practically, integrating the models into a real-time graphical user interface (GUI) demonstrates their feasibility for UAV-based or on-site PV inspection. From an operational and economic perspective, this approach supports cost-effective, scalable, and non-invasive monitoring solutions tailored for modern large-scale solar farms.
- 10 December 2025
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 13 (4) , 712-721
Open AccessComparative Deep Learning for RGB-Based PV Surface Fault Classification Using ResNet50 and EfficientNetB0 with Real-Time Deployment
Photovoltaic (PV) systems are increasingly vital to global energy transitions but remain vulnerable to surface anomalies such as dust, snow, bird droppings, and physical or electrical damage—that significantly reduce power yield and long-term reliability. Manual inspection is inefficient for large-scale solar farms, motivating the development of intelligent and automated fault detection systems. This study introduces a reproducible comparative deep-learning framework that systematically benchmarks four convolutional neural network (CNN) architectures ResNet50, EfficientNetB0, MobileNetV3Small, and DenseNet121 under identical preprocessing, training, and validation settings. The framework integrates runtime efficiency analysis, five-fold cross-validation, and a real-time GUI-based deployment interface, bridging the gap between academic benchmarking and field-level implementation. A six-class labeled dataset of 1,574 RGB images was expanded through extensive data augmentation (rotation, flipping, brightness adjustment, and Gaussian noise perturbation) to simulate diverse real-world conditions. Among the four tested models, DenseNet121 achieved the highest macro-averaged F1-score (≈ 0.96), followed by ResNet50 (0.93), EfficientNetB0 (0.92), and MobileNetV3Small (0.92), highlighting clear accuracy–efficiency trade-offs across architectures. The novelty of this work lies in its multi-model benchmarking design and transparent methodology, providing a standardized and reproducible reference for future PV image-based diagnostics. Practically, integrating the models into a real-time graphical user interface (GUI) demonstrates their feasibility for UAV-based or on-site PV inspection. From an operational and economic perspective, this approach supports cost-effective, scalable, and non-invasive monitoring solutions tailored for modern large-scale solar farms.
- 3 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 33 (3) , 1724-1731
Artificial Intelligence for Streamer Behavior: Predicting Stopping Length in Natural Ester via Current Signal Analysis Using Random Forest
This study presents an intelligent method for predicting the stopping length of streamers by analysing the current signals accompanying streamer propagation in natural ester insulating liquids (specifically, rapeseed oil and olive oil) under AC voltage conditions. A Random Forest regressor was selected on the basis of its fast prediction speed and computational efficiency. Two characteristics derived from the current signals, time domain energy (E) and frequency domain energy (D), served as input parameters, while the experimentally measured streamer stopping length was the output variable. The performance of the model was subjected to rigorous evaluation, employing a range of statistical metrics, including the coefficient of determination (R²), the mean absolute error (MAE), the root mean square error (RMSE), and the mean absolute percentage error (MAPE). The findings demonstrate high R² with low MAEs, RMSEs and MAPEs, indicating robust generalisation ability. These results underscore the effectiveness of the Random Forest regressor in achieving near-perfect prediction accuracy for streamer length estimation, highlighting its potential for real-time applications in insulation diagnostics and high voltage engineering.
- 3 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 33 (3) , 1724-1731
Artificial Intelligence for Streamer Behavior: Predicting Stopping Length in Natural Ester via Current Signal Analysis Using Random Forest
This study presents an intelligent method for predicting the stopping length of streamers by analysing the current signals accompanying streamer propagation in natural ester insulating liquids (specifically, rapeseed oil and olive oil) under AC voltage conditions. A Random Forest regressor was selected on the basis of its fast prediction speed and computational efficiency. Two characteristics derived from the current signals, time domain energy (E) and frequency domain energy (D), served as input parameters, while the experimentally measured streamer stopping length was the output variable. The performance of the model was subjected to rigorous evaluation, employing a range of statistical metrics, including the coefficient of determination (R²), the mean absolute error (MAE), the root mean square error (RMSE), and the mean absolute percentage error (MAPE). The findings demonstrate high R² with low MAEs, RMSEs and MAPEs, indicating robust generalisation ability. These results underscore the effectiveness of the Random Forest regressor in achieving near-perfect prediction accuracy for streamer length estimation, highlighting its potential for real-time applications in insulation diagnostics and high voltage engineering.