Mahdi Emadaleslami
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mahdi Emadaleslami has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Farid Tootoonchian
Electrical Engineering Department, Iran University of Science and Technology, Tehran, Iran
2 shared publications - Maher Abdelkhalek Azzouz
University of Windsor
2 shared publications - MohammadSadegh KhajueeZadeh
Electrical Engineering Department, Sharif University of Technology, Tehran, Iran
2 shared publications - Ahmad Daniar
University of Texas at Dallas, Richardson, TX, USA
1 shared publication - Arash Moradzadeh
Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
1 shared publication - Bilal Akin
Electrical Engineering Department, University of Texas at Dallas, Richardson, TX, USA
1 shared publication
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (5) , 4757-4771
Cyber-Resilient Directional Overcurrent Relays in Distribution Systems Under Data Scarcity
Directional overcurrent relays (DOCRs) are increasingly vulnerable to sophisticated cyberattacks, such as false data injection and time synchronization attacks, which can manipulate measurement data to trigger false tripping or suppress actual faults in distribution systems. While artificial intelligence based methods offer promising capabilities, their dependence on large, balanced datasets limits their usage in protection systems, where labeled fault/cyberattack data is scarce. This paper proposes a Few-Shot Cyber-Attack Detection (Few-CAD) for detecting and classifying both faults and cyberattacks using only a limited number of samples on inverse time and time-current-voltage DOCRs. The Few-CAD operates directly on raw current and voltage signals, eliminating feature extraction. It leverages metric learning with a triplet-loss embedding model to learn a feature space that enables accurate similarity-based event detection, generalization across DOCR modes, and recognition of unseen attack patterns without retraining. The Few-CAD is validated on a Canadian benchmark distribution system under challenging conditions including CT saturation, measurement noise, and data distribution shifts. Results show it outperforms conventional classifiers and few-shot models, achieving high accuracy with as few as five support samples per class, while maintaining effective performance within DOCR timing constraints.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (5) , 4757-4771
Cyber-Resilient Directional Overcurrent Relays in Distribution Systems Under Data Scarcity
Directional overcurrent relays (DOCRs) are increasingly vulnerable to sophisticated cyberattacks, such as false data injection and time synchronization attacks, which can manipulate measurement data to trigger false tripping or suppress actual faults in distribution systems. While artificial intelligence based methods offer promising capabilities, their dependence on large, balanced datasets limits their usage in protection systems, where labeled fault/cyberattack data is scarce. This paper proposes a Few-Shot Cyber-Attack Detection (Few-CAD) for detecting and classifying both faults and cyberattacks using only a limited number of samples on inverse time and time-current-voltage DOCRs. The Few-CAD operates directly on raw current and voltage signals, eliminating feature extraction. It leverages metric learning with a triplet-loss embedding model to learn a feature space that enables accurate similarity-based event detection, generalization across DOCR modes, and recognition of unseen attack patterns without retraining. The Few-CAD is validated on a Canadian benchmark distribution system under challenging conditions including CT saturation, measurement noise, and data distribution shifts. Results show it outperforms conventional classifiers and few-shot models, achieving high accuracy with as few as five support samples per class, while maintaining effective performance within DOCR timing constraints.
- 7 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (11) , 8727-8738
Differential Fault Diagnosis in Power Transformers Under Limited Data Condition via Few-Shot Learning
Power transformers require fast and reliable protection to prevent catastrophic failures. However, collecting labeled fault data in real-world conditions is difficult, as transformers cannot operate under faulted states. This challenge is further complicated by imbalanced datasets and the need for retraining when deploying models on new, unseen transformers, which hinder the effectiveness of artificial intelligence based methods. To address these limitations, we propose Few-DP, a few-shot learning-based differential protection method that operates effectively under limited and imbalanced data. Few-DP uses metric learning and a Siamese convolutional neural network architecture to extract fault features from raw current signals and measure similarity between samples, enabling fault classification with fewer than five examples per class. The model is validated on a simulated 400-kV grid in power systems computer aided design (PSCAD)/electro-magnetic transients in dc systems (EMTDC) and through experimental testing. Results show that Few-DP is robust to noise, data scarcity, saturation, and transformer variability, outperforming state-of-the-art methods in both accuracy and generalization. All simulation models and code are available on GitHub to support future research and development.
- 7 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (11) , 8727-8738
Differential Fault Diagnosis in Power Transformers Under Limited Data Condition via Few-Shot Learning
Power transformers require fast and reliable protection to prevent catastrophic failures. However, collecting labeled fault data in real-world conditions is difficult, as transformers cannot operate under faulted states. This challenge is further complicated by imbalanced datasets and the need for retraining when deploying models on new, unseen transformers, which hinder the effectiveness of artificial intelligence based methods. To address these limitations, we propose Few-DP, a few-shot learning-based differential protection method that operates effectively under limited and imbalanced data. Few-DP uses metric learning and a Siamese convolutional neural network architecture to extract fault features from raw current signals and measure similarity between samples, enabling fault classification with fewer than five examples per class. The model is validated on a simulated 400-kV grid in power systems computer aided design (PSCAD)/electro-magnetic transients in dc systems (EMTDC) and through experimental testing. Results show that Few-DP is robust to noise, data scarcity, saturation, and transformer variability, outperforming state-of-the-art methods in both accuracy and generalization. All simulation models and code are available on GitHub to support future research and development.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-9
Static Eccentricity Fault Location Diagnosis in Resolvers Using Siamese-Based Few-Shot Learning
Static eccentricity in the resolver, with higher probability and severity occurrence, gradually injects instability into the drive system; thus, its exact location diagnosis is mandatory. Whereas most existing investigations rely on frequency analysis of signal voltages for resolver fault diagnosis, artificial intelligence (AI) is at the center of attention for electric motors fault diagnosis. Yet, sufficient data collection brings some challenges for AI. Therefore, intrigued by the idea of few-shot learning to overcome the data scarcity challenge, a Convolutional Neural Siamese network is employed with limited data to diagnose the static eccentricity location under each stator tooth via raw signal voltages, which is ordinarily employed for rotor angle extraction. Accordingly, a Siamese network learns to yield the probability of signal pairs being similar by distance unit. A lab-built Time-Stepping Finite Element Analysis (TS-FEA) and a resolver test-bench dataset under different training sizes, noise existence, and new unseen locations challenges are employed to assess the employed Siamese network. Comparing the employed Siamese network with One Dimension-Convolutional Neural Network (1D-CNN) shows its proficiency and superiority.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-9
Static Eccentricity Fault Location Diagnosis in Resolvers Using Siamese-Based Few-Shot Learning
Static eccentricity in the resolver, with higher probability and severity occurrence, gradually injects instability into the drive system; thus, its exact location diagnosis is mandatory. Whereas most existing investigations rely on frequency analysis of signal voltages for resolver fault diagnosis, artificial intelligence (AI) is at the center of attention for electric motors fault diagnosis. Yet, sufficient data collection brings some challenges for AI. Therefore, intrigued by the idea of few-shot learning to overcome the data scarcity challenge, a Convolutional Neural Siamese network is employed with limited data to diagnose the static eccentricity location under each stator tooth via raw signal voltages, which is ordinarily employed for rotor angle extraction. Accordingly, a Siamese network learns to yield the probability of signal pairs being similar by distance unit. A lab-built Time-Stepping Finite Element Analysis (TS-FEA) and a resolver test-bench dataset under different training sizes, noise existence, and new unseen locations challenges are employed to assess the employed Siamese network. Comparing the employed Siamese network with One Dimension-Convolutional Neural Network (1D-CNN) shows its proficiency and superiority.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (17) , 19145-19152
Comprehensive Investigation of the Resolver’s Eccentricity Effect on the Field-Oriented Control of PMSM
Accurate position feedback from a resolver is highly critical for high-performance field-oriented control (FOC) drives, and eccentricity in resolvers negatively affects the drive performance. The current unbalance intensity (CUI) of permanent magnet synchronous motors (PMSM) is a known criterion to evaluate drive stability and can be caused by position feedback error. In this paper, the eccentric resolver operation is comprehensively investigated, and the corresponding CUI is analytically evaluated. Accordingly, the error limit is defined for an acceptable operation under eccentricity without derating the motor control. For this purpose, the relationship between the (a) resolver’s physical geometry, (b) magnitude and the angle of the stator current, and (c) resolver accuracy are presented through surrogate modeling. Using the proposed analytical current model, the resolver geometry is updated in order to improve the eccentricity tolerance and accuracy and lower the CUI. An optimized rotor design is built, and its accuracy and effect on CUI mitigation are experimentally verified.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (17) , 19145-19152
Comprehensive Investigation of the Resolver’s Eccentricity Effect on the Field-Oriented Control of PMSM
Accurate position feedback from a resolver is highly critical for high-performance field-oriented control (FOC) drives, and eccentricity in resolvers negatively affects the drive performance. The current unbalance intensity (CUI) of permanent magnet synchronous motors (PMSM) is a known criterion to evaluate drive stability and can be caused by position feedback error. In this paper, the eccentric resolver operation is comprehensively investigated, and the corresponding CUI is analytically evaluated. Accordingly, the error limit is defined for an acceptable operation under eccentricity without derating the motor control. For this purpose, the relationship between the (a) resolver’s physical geometry, (b) magnitude and the angle of the stator current, and (c) resolver accuracy are presented through surrogate modeling. Using the proposed analytical current model, the resolver geometry is updated in order to improve the eccentricity tolerance and accuracy and lower the CUI. An optimized rotor design is built, and its accuracy and effect on CUI mitigation are experimentally verified.