Hamza Adaika
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hamza Adaika has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Mohamed Sahraoui
LGEB Laboratory, University of Biskra, Biskra 07000, Algeria
3 shared publications - Zoheir Tir
LEVRES Laboratory, University of El Oued, El Oued 39000, Algeria
3 shared publications - Khaled Laadjal
IREC—Catalonia Institute for Energy Research, Jardins de les Dones de Negre 1, planta 2, 08930 Sant Adrià del Besòs, Barcelona, Spain
2 shared publications - Abdelkader Mahmoudi
UDERZA Unit, Mechanical Department, Faculty of Technology, University of El Oued, 39000 El Oued, Algeria
1 shared publication - Mohammed Adaika
LPMRN Laboratory, Department of Electromechanical Engineering, University of Bordj Bou Arreridj, El-Anasser, 34030, Bordj Bou Arreridj, Algeria
1 shared publication - Mosbah Laouamer
University of ElOued
1 shared publication
Latest Publications
- Open Access
Deep Learning-Enhanced Fault Detection and Localization in Induction Motor Drives: A ResMLP and TCN Framework
Unbalanced supply voltage (USV) represents a critical power quality challenge in industrial environments, significantly degrading the performance, efficiency, and operational lifespan of three-phase induction motors. Accurate real-time estimation of sequence impedances () and detection of the Negative Voltage Factor (NVF) are essential for effective condition monitoring and preventive maintenance strategies. While existing machine learning methods have demonstrated promising accuracy, they often rely on manual feature engineering, lack hierarchical representation learning, and treat impedance estimation and fault detection as isolated tasks. This paper proposes a unified Deep Multi-Task Learning framework that leverages Residual Multilayer Perceptron (ResMLP) architectures for feature-based learning and Temporal Convolutional Networks (TCNs) for end-to-end raw signal learning. Our contributions include: (1) introduction of a Multi-Head ResMLP architecture that jointly optimizes phase impedance and fault detection, achieving superior NVF accuracy (MAE = 0.0007) and a fault detection F1-score of 0.8831; (2) investigation of raw-voltage TCN models for voltage-only diagnostics, with analysis of the trade-offs between end-to-end learning and feature-based approaches; (3) extensive ablation studies demonstrating the impact of network depth, data augmentation, and training protocols on model generalization; and (4) deployment of PyTorch (v2.0.1)-based models suitable for embedded systems with real-time inference capabilities (2.3 ms per prediction). Experimental validation on a 1.1 kW three-phase motor dataset under diverse load conditions (0–10 Nm) and USV magnitudes (5–15 V) confirms the robustness and practical applicability of the proposed approach for industrial fault diagnosis and condition monitoring systems.Open AccessDeep Learning-Enhanced Fault Detection and Localization in Induction Motor Drives: A ResMLP and TCN Framework
Unbalanced supply voltage (USV) represents a critical power quality challenge in industrial environments, significantly degrading the performance, efficiency, and operational lifespan of three-phase induction motors. Accurate real-time estimation of sequence impedances () and detection of the Negative Voltage Factor (NVF) are essential for effective condition monitoring and preventive maintenance strategies. While existing machine learning methods have demonstrated promising accuracy, they often rely on manual feature engineering, lack hierarchical representation learning, and treat impedance estimation and fault detection as isolated tasks. This paper proposes a unified Deep Multi-Task Learning framework that leverages Residual Multilayer Perceptron (ResMLP) architectures for feature-based learning and Temporal Convolutional Networks (TCNs) for end-to-end raw signal learning. Our contributions include: (1) introduction of a Multi-Head ResMLP architecture that jointly optimizes phase impedance and fault detection, achieving superior NVF accuracy (MAE = 0.0007) and a fault detection F1-score of 0.8831; (2) investigation of raw-voltage TCN models for voltage-only diagnostics, with analysis of the trade-offs between end-to-end learning and feature-based approaches; (3) extensive ablation studies demonstrating the impact of network depth, data augmentation, and training protocols on model generalization; and (4) deployment of PyTorch (v2.0.1)-based models suitable for embedded systems with real-time inference capabilities (2.3 ms per prediction). Experimental validation on a 1.1 kW three-phase motor dataset under diverse load conditions (0–10 Nm) and USV magnitudes (5–15 V) confirms the robustness and practical applicability of the proposed approach for industrial fault diagnosis and condition monitoring systems. - 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.
- Open Access
PumpSpectra: An MCSA-Based Platform for Fault Detection in Centrifugal Pump Systems
Reliable detection of faults in centrifugal pump systems is challenging in industrial environments due to harsh operating conditions, limited sensor access, and the need for fast, explainable decisions. We developed PumpSpectra, an industrial Motor Current Signature Analysis (MCSA) platform that processes uploaded stator-current CSV files using FFT/STFT with transparent, rule-based models designed to identify mechanical faults including misalignment, bearing defects, and impeller anomalies; field validation demonstrated misalignment detection. In a case study at the El Oued desalination plant (Algeria; operating points), PumpSpectra achieved 91.2% diagnostic accuracy with a 95% reduction in analysis time compared to manual MCSA post-processing, and a false-positive rate of 3.8% at 0.1 Hz resolution. These results suggest that current-only, explainable analytics can support predictive maintenance programs by accelerating fault triage, improving traceability of decisions, and reducing avoided maintenance costs in pump-driven industrial assets.Open AccessPumpSpectra: An MCSA-Based Platform for Fault Detection in Centrifugal Pump Systems
Reliable detection of faults in centrifugal pump systems is challenging in industrial environments due to harsh operating conditions, limited sensor access, and the need for fast, explainable decisions. We developed PumpSpectra, an industrial Motor Current Signature Analysis (MCSA) platform that processes uploaded stator-current CSV files using FFT/STFT with transparent, rule-based models designed to identify mechanical faults including misalignment, bearing defects, and impeller anomalies; field validation demonstrated misalignment detection. In a case study at the El Oued desalination plant (Algeria; operating points), PumpSpectra achieved 91.2% diagnostic accuracy with a 95% reduction in analysis time compared to manual MCSA post-processing, and a false-positive rate of 3.8% at 0.1 Hz resolution. These results suggest that current-only, explainable analytics can support predictive maintenance programs by accelerating fault triage, improving traceability of decisions, and reducing avoided maintenance costs in pump-driven industrial assets. - Open Access
- 21 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 764-768
Diagnosis of Rotor Broken Bar Faults in Induction Motors Using the CNN-Based Current Signal
In industrial contexts, the efficient operation of induction motors is paramount, necessitating robust condition monitoring and fault diagnosis techniques to mitigate costly disruptions. This research shows a way to use the "Signal2Image" method and convolutional neural networks (CNN) to intelligently find broken rotor bars in induction motors. Our method automatically pulls out important features from input data by using a large current signal dataset from Western Parana State University. This dataset includes different levels of broken rotor bar (BRB) faults and different loading conditions. The "Signal2Image" process transforms time-domain current signals into 2D grayscale pixel images, facilitating CNN-based image classification to identify fault-related patterns. We achieve an impressive fault classification accuracy of 88% across all fault cases through meticulous CNN parameter tuning while optimizing computational efficiency. A significant contribution of this work is the substantial reduction in computational time for fault classification, surpassing existing approaches. This research enhances fault detection accuracy and streamlines the process, contributing to the field of predictive maintenance for induction motors.
- 21 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 764-768
Open AccessDiagnosis of Rotor Broken Bar Faults in Induction Motors Using the CNN-Based Current Signal
In industrial contexts, the efficient operation of induction motors is paramount, necessitating robust condition monitoring and fault diagnosis techniques to mitigate costly disruptions. This research shows a way to use the "Signal2Image" method and convolutional neural networks (CNN) to intelligently find broken rotor bars in induction motors. Our method automatically pulls out important features from input data by using a large current signal dataset from Western Parana State University. This dataset includes different levels of broken rotor bar (BRB) faults and different loading conditions. The "Signal2Image" process transforms time-domain current signals into 2D grayscale pixel images, facilitating CNN-based image classification to identify fault-related patterns. We achieve an impressive fault classification accuracy of 88% across all fault cases through meticulous CNN parameter tuning while optimizing computational efficiency. A significant contribution of this work is the substantial reduction in computational time for fault classification, surpassing existing approaches. This research enhances fault detection accuracy and streamlines the process, contributing to the field of predictive maintenance for induction motors.