Hassan Ezzaidi - Academia.edu (original) (raw)

Papers by Hassan Ezzaidi

Research paper thumbnail of Using Deep Learning to Detect Anomalies in On-Load Tap Changer Based on Vibro-Acoustic Signal Features

Research paper thumbnail of Dynamic behavior of impinging drops on water repellent surfaces: Machine learning-assisted approach to predict maximum spreading

Experimental Thermal and Fluid Science

Research paper thumbnail of tDCS Task-Oriented Approach Improves Function in Individuals With Fibromyalgia Pain. A Pilot Study

Frontiers in Pain Research, 2021

Fibromyalgia (FM) is a complex pain syndrome accompanied by physical disability and loss of daily... more Fibromyalgia (FM) is a complex pain syndrome accompanied by physical disability and loss of daily life activities. Evidences suggest that modulation of the primary motor cortex (M1) by transcranial direct current stimulation (tDCS) improves functional physical capacity in chronic pain conditions. However, the gain on physical function in people living with FM receiving tDCS is still unclear. This study aimed to evaluate whether the tDCS task-oriented approach improves function and reduces pain in a single cohort of 10 FM. A total of 10 women with FM (60.4 ± 15.37 years old) were enrolled in an intervention including anodal tDCS delivered on M1 (2 mA from a constant stimulator for 20 min); simultaneously they performed a functional task. The anode was placed on the contralateral hemisphere of the dominant hand. Outcome assessments were done before the stimulation, immediately after stimulation and 30 min after the end of tDCS. The same protocol was applied in subsequent sessions. A t...

Research paper thumbnail of Pitch and MFCC dependent GMM models for speaker identification systems

Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513), 2004

Research paper thumbnail of Temperature Impact on On-load Tap Changers Vibro-Acoustic Signals

Research paper thumbnail of Influence of Transformer Structures on the Frequency Response Analysis: A Laboratory Case Study

2021 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP), Dec 12, 2021

Frequency response analysis (FRA) is used in the electrical industry for condition assessment of ... more Frequency response analysis (FRA) is used in the electrical industry for condition assessment of power transformers. The method is sensitive to even slight variations occurring in the active parts of transformers. Over the years, FRA has demonstrated its good capacity for detection of mechanical and electrical failure modes This paper explores different measurements taken on a laboratory transformer model where the influence of cylindrical grounded structures (simulating a tank and a core) is investigated. The cylindrical structures were added in order to study their impacts on the frequency response with a specific focus on the inductance and capacitance changes. The core and tank influences on the frequency response measurements are explained by shunt capacitances variation in both cases causing similar changes to the traces. Besides, radially induced currents in the tank made of magnetic steel affected the main inductance of the winding causing a shift of the first anti-resonance frequency. Such radially induced currents were prevented by the design of the simulated core made of aluminum strips. The results indicated that the transformer structure has a significant influence on the frequency response, related to changes in the main inductance and capacitances of the equivalent transformer circuit model. These academic experiments help contributing to a better understanding and further support of transformer FRA trace interpretations.

Research paper thumbnail of Filter group delays equalization for 2D discrete wavelet transform applications

Expert Systems With Applications, Aug 1, 2022

Research paper thumbnail of Human-robot collaboration while sharing production activities in dynamic environment: SPADER system

Robotics and Computer-integrated Manufacturing, Dec 1, 2017

Research paper thumbnail of Artificial neural network-based maximum power point tracking control for variable speed wind energy conversion systems

A new maximum power point tracking (MPPT) controller using artificial neural networks (ANN) for v... more A new maximum power point tracking (MPPT) controller using artificial neural networks (ANN) for variable speed wind energy conversion system (WECS) is proposed. The algorithm uses Jordan recurrent ANN and is trained online using back propagation. The inputs to the networks are the instantaneous output power, maximum output power, rotor speed and wind speed, and the output is the rotor

Research paper thumbnail of Real-time implementation of an adaptive noise canceller based on MicroBlaze soft processor

ABSTRACT In this paper, two architectures based on the MicroBlaze soft processor are implemented ... more ABSTRACT In this paper, two architectures based on the MicroBlaze soft processor are implemented on FPGA for real-time adaptive noise cancellation. The first architecture uses the least mean square (LMS) algorithm with 16-bit fixed-point fractional format, while the second one is based on a scaled version of the normalized least mean square (NLMS) algorithm with 16-bit fixed-point integer format. Those architectures were applied to remove, in real-time, the 60 Hz interference from electrocardiogram (ECG) signal with various levels of the reference input.

Research paper thumbnail of Towards the Objective Identification of the Presence of Pain Based on Electroencephalography Signals’ Analysis: A Proof-of-Concept

Research paper thumbnail of Rotating Machinery Condition Monitoring Using Time Series Analysis of Vibration Signal

Research paper thumbnail of Neural Networks Approach for Hyperelastic Behaviour Characterization of ABS under Uniaxial Solicitation

British Journal of Applied Science and Technology, Jan 10, 2014

Research paper thumbnail of Simultaneous Estimation of Speed and Rotor Resistance in Sensorless Induction Motor Vector Controlled Drive

International Journal of Modelling and Simulation, 2007

ABSTRACT In this paper a new sensorless indirect vector controlled induction motor drive robust a... more ABSTRACT In this paper a new sensorless indirect vector controlled induction motor drive robust against rotor resistance variation is presented. The speed and rotor resistance are estimated simultaneously, which is reported in many papers as impossible. The estimation is achieved using a reduced order Kalman filter to reduce the computational burden. This algorithm uses a reduced order model of the motor. The model takes into account the coupling between the electrical and mechanical modes, which is true for small size machines. The method proposed in this paper is applicable to a large category of induction motor drives with a gradually varying load torque such as viscous friction, fan/blower and centrifugal pump. A fully real-time digital simulation, a new powerful tool for rapid control prototyping, is carried out to verify the effectiveness of the proposed method. Results show that accurate estimation is achieved under both transient and steady state conditions without injecting any external signal. This achievement is, to the best of authors' knowledge, reported for the first time and is believed to be of great importance for induction machine sensorless control.

Research paper thumbnail of A Neurophysiological Pattern as a Precursor of Work-Related Musculoskeletal Disorders Using EEG Combined with EMG

International Journal of Environmental Research and Public Health

We aimed to determine the neurophysiological pattern that is associated with the development of m... more We aimed to determine the neurophysiological pattern that is associated with the development of musculoskeletal pain that is induced by biomechanical constraints. Twelve (12) young healthy volunteers (two females) performed two experimental realistic manual tasks for 30 min each: (1) with the high risk of musculoskeletal pain development and (2) with low risk for pain development. During the tasks, synchronized electroencephalographic (EEG) and electromyography (EMG) signals data were collected, as well as pain scores. Subsequently, two main variables were computed from neurophysiological signals: (1) cortical inhibition as Task-Related Power Increase (TRPI) in beta EEG frequency band (β.TRPI) and (2) muscle variability as Coefficient of Variation (CoV) from EMG signals. A strong effect size was observed for pain measurement under the high risk condition during the last 5 min of the task execution; with muscle fatigue, because the CoV has decreased below 18%. An increase in cortical...

Research paper thumbnail of Automatic Musical Genre Classification Using Divergence and Average Information Measures

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, Mar 28, 2008

Research paper thumbnail of Power Transformers OLTC Condition Monitoring Based on Feature Extraction from Vibro-Acoustic Signals: Main Peaks and Euclidean Distance

Sensors

The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in ... more The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in the maintenance of power transformers, which is the most strategic component of the power network substations. Among the OLTC fault detection methods, vibro-acoustic signal analysis is known as a performant approach with the ability to detect many faults of different types. Extracting the characteristic features from the measured vibro-acoustic signal envelopes is a promising approach to precisely diagnose OLTC faults. The present research work is focused on developing a methodology to detect, locate, and track changes in on-line monitored vibro-acoustic signal envelopes based on the main peaks extraction and Euclidean distance analysis. OLTC monitoring systems have been installed on power transformers in services which allowed the recording of a rich dataset of vibro-acoustic signal envelopes in real time. The proposed approach was applied on six different datasets and a detailed analys...

Research paper thumbnail of Reproducing Transformers’ Frequency Response from Finite Element Method (FEM) Simulation and Parameters Optimization

Energies

Frequency response analysis (FRA) is being employed worldwide as one of the main methods for the ... more Frequency response analysis (FRA) is being employed worldwide as one of the main methods for the internal condition assessment of transformers due to its capability of detecting mechanical changes. Nonetheless, the objective interpretation of FRA measurements is still a challenge for the industry. This is mainly attributable to the lack of complete data from the same or similar units. A large database of FRA measurements can contribute to improving classification algorithms and lead to a more objective interpretation. Due to their destructive nature, mechanical deformations cannot be performed on real transformers to collect data from different scenarios. The use of simulation and laboratory transformer models is necessary. This research contribution is based on a new method using Finite Element Method simulation and a lumped element circuit to obtain FRA traces from a laboratory model at healthy and faulty states, along with an optimization method to improve capacitive parameters f...

Research paper thumbnail of A Machine-Learning Approach to Identify the Influence of Temperature on FRA Measurements

Energies, 2021

Frequency response analysis (FRA) is a powerful and widely used tool for condition assessment in ... more Frequency response analysis (FRA) is a powerful and widely used tool for condition assessment in power transformers. However, interpretation schemes are still challenging. Studies show that FRA data can be influenced by parameters other than winding deformation, including temperature. In this study, a machine-learning approach with temperature as an input attribute was used to objectively identify faults in FRA traces. To the best knowledge of the authors, this has not been reported in the literature. A single-phase transformer model was specifically designed and fabricated for use as a test object for the study. The model is unique in that it allows the non-destructive interchange of healthy and distorted winding sections and, hence, reproducible and repeatable FRA measurements. FRA measurements taken at temperatures ranging from −40 °C to 40 °C were used first to describe the impact of temperature on FRA traces and then to test the ability of the machine learning algorithms to dis...

Research paper thumbnail of Experimental investigation of internal defect detection of a 69-kV composite insulator

2016 IEEE Electrical Insulation Conference (EIC), 2016

This paper presents an experimental investigation of semi-conductive internal defects present in ... more This paper presents an experimental investigation of semi-conductive internal defects present in a 69 kV composite insulator based on E-field measurements. For this purpose, an electro-optic sensor with compact E-field probe was used. In order to simulate the presence of internal defects, an experimental 69 kV composite insulator was specially developed using 3D printing. The results demonstrate that the proposed 69-kV experimental model obtained from 3D printing can be a new alternative for adequate simulation and study of internal defects present in composite insulators. Moreover, these results also show that the actual E-field method used for detecting internal defects can be considerably improved by measuring the radial E-field component close to the rod sheath surface, between insulator sheds. Using this approach, semi-conductive defects with a length equal to 3.5% of the insulator length can be detected both at the HV electrode and floating potential, with is a significant improvement of the sensitivity of actual E-field detection method.

Research paper thumbnail of Using Deep Learning to Detect Anomalies in On-Load Tap Changer Based on Vibro-Acoustic Signal Features

Research paper thumbnail of Dynamic behavior of impinging drops on water repellent surfaces: Machine learning-assisted approach to predict maximum spreading

Experimental Thermal and Fluid Science

Research paper thumbnail of tDCS Task-Oriented Approach Improves Function in Individuals With Fibromyalgia Pain. A Pilot Study

Frontiers in Pain Research, 2021

Fibromyalgia (FM) is a complex pain syndrome accompanied by physical disability and loss of daily... more Fibromyalgia (FM) is a complex pain syndrome accompanied by physical disability and loss of daily life activities. Evidences suggest that modulation of the primary motor cortex (M1) by transcranial direct current stimulation (tDCS) improves functional physical capacity in chronic pain conditions. However, the gain on physical function in people living with FM receiving tDCS is still unclear. This study aimed to evaluate whether the tDCS task-oriented approach improves function and reduces pain in a single cohort of 10 FM. A total of 10 women with FM (60.4 ± 15.37 years old) were enrolled in an intervention including anodal tDCS delivered on M1 (2 mA from a constant stimulator for 20 min); simultaneously they performed a functional task. The anode was placed on the contralateral hemisphere of the dominant hand. Outcome assessments were done before the stimulation, immediately after stimulation and 30 min after the end of tDCS. The same protocol was applied in subsequent sessions. A t...

Research paper thumbnail of Pitch and MFCC dependent GMM models for speaker identification systems

Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513), 2004

Research paper thumbnail of Temperature Impact on On-load Tap Changers Vibro-Acoustic Signals

Research paper thumbnail of Influence of Transformer Structures on the Frequency Response Analysis: A Laboratory Case Study

2021 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP), Dec 12, 2021

Frequency response analysis (FRA) is used in the electrical industry for condition assessment of ... more Frequency response analysis (FRA) is used in the electrical industry for condition assessment of power transformers. The method is sensitive to even slight variations occurring in the active parts of transformers. Over the years, FRA has demonstrated its good capacity for detection of mechanical and electrical failure modes This paper explores different measurements taken on a laboratory transformer model where the influence of cylindrical grounded structures (simulating a tank and a core) is investigated. The cylindrical structures were added in order to study their impacts on the frequency response with a specific focus on the inductance and capacitance changes. The core and tank influences on the frequency response measurements are explained by shunt capacitances variation in both cases causing similar changes to the traces. Besides, radially induced currents in the tank made of magnetic steel affected the main inductance of the winding causing a shift of the first anti-resonance frequency. Such radially induced currents were prevented by the design of the simulated core made of aluminum strips. The results indicated that the transformer structure has a significant influence on the frequency response, related to changes in the main inductance and capacitances of the equivalent transformer circuit model. These academic experiments help contributing to a better understanding and further support of transformer FRA trace interpretations.

Research paper thumbnail of Filter group delays equalization for 2D discrete wavelet transform applications

Expert Systems With Applications, Aug 1, 2022

Research paper thumbnail of Human-robot collaboration while sharing production activities in dynamic environment: SPADER system

Robotics and Computer-integrated Manufacturing, Dec 1, 2017

Research paper thumbnail of Artificial neural network-based maximum power point tracking control for variable speed wind energy conversion systems

A new maximum power point tracking (MPPT) controller using artificial neural networks (ANN) for v... more A new maximum power point tracking (MPPT) controller using artificial neural networks (ANN) for variable speed wind energy conversion system (WECS) is proposed. The algorithm uses Jordan recurrent ANN and is trained online using back propagation. The inputs to the networks are the instantaneous output power, maximum output power, rotor speed and wind speed, and the output is the rotor

Research paper thumbnail of Real-time implementation of an adaptive noise canceller based on MicroBlaze soft processor

ABSTRACT In this paper, two architectures based on the MicroBlaze soft processor are implemented ... more ABSTRACT In this paper, two architectures based on the MicroBlaze soft processor are implemented on FPGA for real-time adaptive noise cancellation. The first architecture uses the least mean square (LMS) algorithm with 16-bit fixed-point fractional format, while the second one is based on a scaled version of the normalized least mean square (NLMS) algorithm with 16-bit fixed-point integer format. Those architectures were applied to remove, in real-time, the 60 Hz interference from electrocardiogram (ECG) signal with various levels of the reference input.

Research paper thumbnail of Towards the Objective Identification of the Presence of Pain Based on Electroencephalography Signals’ Analysis: A Proof-of-Concept

Research paper thumbnail of Rotating Machinery Condition Monitoring Using Time Series Analysis of Vibration Signal

Research paper thumbnail of Neural Networks Approach for Hyperelastic Behaviour Characterization of ABS under Uniaxial Solicitation

British Journal of Applied Science and Technology, Jan 10, 2014

Research paper thumbnail of Simultaneous Estimation of Speed and Rotor Resistance in Sensorless Induction Motor Vector Controlled Drive

International Journal of Modelling and Simulation, 2007

ABSTRACT In this paper a new sensorless indirect vector controlled induction motor drive robust a... more ABSTRACT In this paper a new sensorless indirect vector controlled induction motor drive robust against rotor resistance variation is presented. The speed and rotor resistance are estimated simultaneously, which is reported in many papers as impossible. The estimation is achieved using a reduced order Kalman filter to reduce the computational burden. This algorithm uses a reduced order model of the motor. The model takes into account the coupling between the electrical and mechanical modes, which is true for small size machines. The method proposed in this paper is applicable to a large category of induction motor drives with a gradually varying load torque such as viscous friction, fan/blower and centrifugal pump. A fully real-time digital simulation, a new powerful tool for rapid control prototyping, is carried out to verify the effectiveness of the proposed method. Results show that accurate estimation is achieved under both transient and steady state conditions without injecting any external signal. This achievement is, to the best of authors' knowledge, reported for the first time and is believed to be of great importance for induction machine sensorless control.

Research paper thumbnail of A Neurophysiological Pattern as a Precursor of Work-Related Musculoskeletal Disorders Using EEG Combined with EMG

International Journal of Environmental Research and Public Health

We aimed to determine the neurophysiological pattern that is associated with the development of m... more We aimed to determine the neurophysiological pattern that is associated with the development of musculoskeletal pain that is induced by biomechanical constraints. Twelve (12) young healthy volunteers (two females) performed two experimental realistic manual tasks for 30 min each: (1) with the high risk of musculoskeletal pain development and (2) with low risk for pain development. During the tasks, synchronized electroencephalographic (EEG) and electromyography (EMG) signals data were collected, as well as pain scores. Subsequently, two main variables were computed from neurophysiological signals: (1) cortical inhibition as Task-Related Power Increase (TRPI) in beta EEG frequency band (β.TRPI) and (2) muscle variability as Coefficient of Variation (CoV) from EMG signals. A strong effect size was observed for pain measurement under the high risk condition during the last 5 min of the task execution; with muscle fatigue, because the CoV has decreased below 18%. An increase in cortical...

Research paper thumbnail of Automatic Musical Genre Classification Using Divergence and Average Information Measures

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, Mar 28, 2008

Research paper thumbnail of Power Transformers OLTC Condition Monitoring Based on Feature Extraction from Vibro-Acoustic Signals: Main Peaks and Euclidean Distance

Sensors

The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in ... more The detection of On-Load Tap-Changer (OLTC) faults at an early stage plays a significant role in the maintenance of power transformers, which is the most strategic component of the power network substations. Among the OLTC fault detection methods, vibro-acoustic signal analysis is known as a performant approach with the ability to detect many faults of different types. Extracting the characteristic features from the measured vibro-acoustic signal envelopes is a promising approach to precisely diagnose OLTC faults. The present research work is focused on developing a methodology to detect, locate, and track changes in on-line monitored vibro-acoustic signal envelopes based on the main peaks extraction and Euclidean distance analysis. OLTC monitoring systems have been installed on power transformers in services which allowed the recording of a rich dataset of vibro-acoustic signal envelopes in real time. The proposed approach was applied on six different datasets and a detailed analys...

Research paper thumbnail of Reproducing Transformers’ Frequency Response from Finite Element Method (FEM) Simulation and Parameters Optimization

Energies

Frequency response analysis (FRA) is being employed worldwide as one of the main methods for the ... more Frequency response analysis (FRA) is being employed worldwide as one of the main methods for the internal condition assessment of transformers due to its capability of detecting mechanical changes. Nonetheless, the objective interpretation of FRA measurements is still a challenge for the industry. This is mainly attributable to the lack of complete data from the same or similar units. A large database of FRA measurements can contribute to improving classification algorithms and lead to a more objective interpretation. Due to their destructive nature, mechanical deformations cannot be performed on real transformers to collect data from different scenarios. The use of simulation and laboratory transformer models is necessary. This research contribution is based on a new method using Finite Element Method simulation and a lumped element circuit to obtain FRA traces from a laboratory model at healthy and faulty states, along with an optimization method to improve capacitive parameters f...

Research paper thumbnail of A Machine-Learning Approach to Identify the Influence of Temperature on FRA Measurements

Energies, 2021

Frequency response analysis (FRA) is a powerful and widely used tool for condition assessment in ... more Frequency response analysis (FRA) is a powerful and widely used tool for condition assessment in power transformers. However, interpretation schemes are still challenging. Studies show that FRA data can be influenced by parameters other than winding deformation, including temperature. In this study, a machine-learning approach with temperature as an input attribute was used to objectively identify faults in FRA traces. To the best knowledge of the authors, this has not been reported in the literature. A single-phase transformer model was specifically designed and fabricated for use as a test object for the study. The model is unique in that it allows the non-destructive interchange of healthy and distorted winding sections and, hence, reproducible and repeatable FRA measurements. FRA measurements taken at temperatures ranging from −40 °C to 40 °C were used first to describe the impact of temperature on FRA traces and then to test the ability of the machine learning algorithms to dis...

Research paper thumbnail of Experimental investigation of internal defect detection of a 69-kV composite insulator

2016 IEEE Electrical Insulation Conference (EIC), 2016

This paper presents an experimental investigation of semi-conductive internal defects present in ... more This paper presents an experimental investigation of semi-conductive internal defects present in a 69 kV composite insulator based on E-field measurements. For this purpose, an electro-optic sensor with compact E-field probe was used. In order to simulate the presence of internal defects, an experimental 69 kV composite insulator was specially developed using 3D printing. The results demonstrate that the proposed 69-kV experimental model obtained from 3D printing can be a new alternative for adequate simulation and study of internal defects present in composite insulators. Moreover, these results also show that the actual E-field method used for detecting internal defects can be considerably improved by measuring the radial E-field component close to the rod sheath surface, between insulator sheds. Using this approach, semi-conductive defects with a length equal to 3.5% of the insulator length can be detected both at the HV electrode and floating potential, with is a significant improvement of the sensitivity of actual E-field detection method.