Innocent Enyekwe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Innocent Enyekwe has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Kwang Y. Lee
Baylor University,Electrical and Computer Engineering,Waco,Texas,USA,76798
2 shared publications- Kwang Y. Lee
Department of Electrical and Computer Engineering, Baylor University, Waco, TX, USA
2 shared publications Soumyadeep Nag
University of Central Florida, Orlando, FL 32816 USA
2 shared publications- Wenlei Bai
Oracle Energy and Water, Austin, TX, United States of America
2 shared publications - Emmanuel B. Agamloh
Department of Electrical and Computer Engineering, Baylor University, Waco, TX 76798, USA
1 shared publication Joseph Holden
Electrical and Computer Engineering Baylor University, Waco, Texas, USA
1 shared publication
Latest Publications
- Open Access
Rotating Electric Machine Fault Diagnosis with Magnetic Flux Measurement Using Deep Learning Models
This paper presents new techniques for electric machine diagnostics that combine advanced signal processing and artificial intelligence (AI)-based techniques using magnetic flux measurements acquired under various operating conditions. Developing an effective electric machine diagnostics tool is paramount for increased industrial productivity and extending the service life of the machine. The existing diagnostic tools face issues, including false indication of faults using classical methods, and the proposed data-driven methods based on machine learning lack transferability of model knowledge on an unseen dataset from different motor types or power ratings due to structural differences. To overcome these diagnostic drawbacks of statistical ML classifiers and classical approaches, innovative feature selection methods were employed in this work to preprocess the measured magnetic flux into a spectrogram image, and the transfer learning (TL) technique was applied to fine-tune convolution neural networks (CNNs) ImageNet pretrained models. The experimental results show the trained statistical ML classifiers and traditional CNN performance on unseen BU data and on the external data, and the performance demonstrated a lack of generalization on external datasets of different power ratings or structures. Models with such drawbacks cannot be used for developing effective diagnostic systems. The TL technique was employed on different deep CNN ImageNet pretrained models with spectrogram images as inputs to the deep CN network. This approach demonstrated an advanced and improved electric machine diagnostic system that addresses the drawbacks of the current ML-based diagnostic systems. The generalized model developed using CNN ResNet50 outperformed other deep CNN ImageNet models in correctly diagnosing faults on both the dataset generated from the authors’ lab and on an external dataset of a different machine from another research lab.
Open AccessRotating Electric Machine Fault Diagnosis with Magnetic Flux Measurement Using Deep Learning Models
This paper presents new techniques for electric machine diagnostics that combine advanced signal processing and artificial intelligence (AI)-based techniques using magnetic flux measurements acquired under various operating conditions. Developing an effective electric machine diagnostics tool is paramount for increased industrial productivity and extending the service life of the machine. The existing diagnostic tools face issues, including false indication of faults using classical methods, and the proposed data-driven methods based on machine learning lack transferability of model knowledge on an unseen dataset from different motor types or power ratings due to structural differences. To overcome these diagnostic drawbacks of statistical ML classifiers and classical approaches, innovative feature selection methods were employed in this work to preprocess the measured magnetic flux into a spectrogram image, and the transfer learning (TL) technique was applied to fine-tune convolution neural networks (CNNs) ImageNet pretrained models. The experimental results show the trained statistical ML classifiers and traditional CNN performance on unseen BU data and on the external data, and the performance demonstrated a lack of generalization on external datasets of different power ratings or structures. Models with such drawbacks cannot be used for developing effective diagnostic systems. The TL technique was employed on different deep CNN ImageNet pretrained models with spectrogram images as inputs to the deep CN network. This approach demonstrated an advanced and improved electric machine diagnostic system that addresses the drawbacks of the current ML-based diagnostic systems. The generalized model developed using CNN ResNet50 outperformed other deep CNN ImageNet models in correctly diagnosing faults on both the dataset generated from the authors’ lab and on an external dataset of a different machine from another research lab.
- Open Access
A Comparative Study of Optimal PV Allocation in a Distribution Network Using Evolutionary Algorithms
The growing distributed energy resource (DER) penetration into distribution networks, such as through residential and commercial photovoltaics (PV), has emerged through a transition from passive to active networks, which takes the complexity of planning and operations to the next level. Optimal PV allocation (sizing and location) is challenging because it involves mixed-integer non-linear programming with three-phase non-linear unbalanced power flow equations. Meta-heuristic algorithms have proven their effectiveness in many complex engineering problems. Thus, in this study, we propose to achieve optimal PV allocation by using several basic evolutionary algorithms (EAs), particle swarm optimization (PSO), artificial bee colony (ABC), differential evolution (DE), and their variants, all of which are applied for a study of their performance levels. Two modified unbalanced IEEE test feeders (13 and 37 bus) are developed to evaluate these performance levels, with two objectives: one is to maximize PV penetration, and the other is to minimize the voltage deviation from 1.0 p.u. To handle the computational burden of the sequential power flow and unbalanced network, we adopt an efficient iterative load flow algorithm instead of the commonly used and yet highly simplified forward–backward sweep method. A comparative study of these basic EAs shows their general success in finding a near-optimal solution, except in the case of the DE, which is known for solving continuous optimization problems efficiently. From experiments run 30 times, it is observed that PSO-related algorithms are more efficient and robust in the maximum PV penetration case, while ABC-related algorithms are more efficient and robust in the minimum voltage deviation case.
Open AccessA Comparative Study of Optimal PV Allocation in a Distribution Network Using Evolutionary Algorithms
The growing distributed energy resource (DER) penetration into distribution networks, such as through residential and commercial photovoltaics (PV), has emerged through a transition from passive to active networks, which takes the complexity of planning and operations to the next level. Optimal PV allocation (sizing and location) is challenging because it involves mixed-integer non-linear programming with three-phase non-linear unbalanced power flow equations. Meta-heuristic algorithms have proven their effectiveness in many complex engineering problems. Thus, in this study, we propose to achieve optimal PV allocation by using several basic evolutionary algorithms (EAs), particle swarm optimization (PSO), artificial bee colony (ABC), differential evolution (DE), and their variants, all of which are applied for a study of their performance levels. Two modified unbalanced IEEE test feeders (13 and 37 bus) are developed to evaluate these performance levels, with two objectives: one is to maximize PV penetration, and the other is to minimize the voltage deviation from 1.0 p.u. To handle the computational burden of the sequential power flow and unbalanced network, we adopt an efficient iterative load flow algorithm instead of the commonly used and yet highly simplified forward–backward sweep method. A comparative study of these basic EAs shows their general success in finding a near-optimal solution, except in the case of the DE, which is known for solving continuous optimization problems efficiently. From experiments run 30 times, it is observed that PSO-related algorithms are more efficient and robust in the maximum PV penetration case, while ABC-related algorithms are more efficient and robust in the minimum voltage deviation case.
- 22 November 2023
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 56 (2) , 10929-10934
Neural Network-Based Control for Hybrid PV and Adjustable Speed Pumped-Storage Hydropower Plant
- 22 November 2023
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 56 (2) , 10929-10934
Neural Network-Based Control for Hybrid PV and Adjustable Speed Pumped-Storage Hydropower Plant
- 19 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Grid-Forming Control with DFIM based Adjustable Speed Pumped-Storage Hydropower
Adjustable speed pumped-storage hydropower (AS – PSH) can add significant benefits to the power system network. However, AS-PSH today is designed as a grid-following unit. Therefore, unlike the conventional PSH, this grid-following control (GFLC) based AS-PSH loses the capability to black-start the power system unless special measures are taken. To overcome this drawback, a flux-tracking-based grid-forming control (GFMC) for AS-PSH is designed. The PI controllers are designed using an adaptive framework to cope with the time-varying AS-PSH, power network systems. This paper presents the preliminary investigations using simulations in MATLAB/Simulink to indicate that the GFMC for the AS-PSH system can successfully black-start the power system, while also working at optimal speeds to maximize efficiency of the AS-PSH system.
- 19 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Grid-Forming Control with DFIM based Adjustable Speed Pumped-Storage Hydropower
Adjustable speed pumped-storage hydropower (AS – PSH) can add significant benefits to the power system network. However, AS-PSH today is designed as a grid-following unit. Therefore, unlike the conventional PSH, this grid-following control (GFLC) based AS-PSH loses the capability to black-start the power system unless special measures are taken. To overcome this drawback, a flux-tracking-based grid-forming control (GFMC) for AS-PSH is designed. The PI controllers are designed using an adaptive framework to cope with the time-varying AS-PSH, power network systems. This paper presents the preliminary investigations using simulations in MATLAB/Simulink to indicate that the GFMC for the AS-PSH system can successfully black-start the power system, while also working at optimal speeds to maximize efficiency of the AS-PSH system.
- Open Access
- 1 January 2023
- Published by Avestia Publishing in Journal of Machine Intelligence and Data Science
- Vol. 4 (1) , 27-34
Speed Control of an Adjustable Speed Pumped Storage Hydropower Plant with a Deep Reinforcement Learning-Based Governor
- 1 January 2023
- Published by Avestia Publishing in Journal of Machine Intelligence and Data Science
- Vol. 4 (1) , 27-34
Open AccessSpeed Control of an Adjustable Speed Pumped Storage Hydropower Plant with a Deep Reinforcement Learning-Based Governor
- 14 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Neural Network-Based Modeling for A Solid-Oxide Fuel Cell Stack
With the growing concerns about the environment, more effort has been put towards reducing the pollutant gases generated in the electric power sector by integrating distributed energy conversion devices with high efficiency and low emission. However, these devices such as fuel cells come with their shortcomings and challenges of meeting lifetime and availability goals, especially when operated outside their safe operational range. Therefore, the need to develop not just good controls but also intelligent controls arise to help respect these constraints while meeting up with the load demands. In this paper, Neural Networks (NN s) were used as a system identifier to model the dynamics of a solid-oxide fuel cell (SOFC) stack to be used in the controller design. The proposed NN model was validated by comparing its results with that of an already validated mathematical model.
- 14 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Neural Network-Based Modeling for A Solid-Oxide Fuel Cell Stack
With the growing concerns about the environment, more effort has been put towards reducing the pollutant gases generated in the electric power sector by integrating distributed energy conversion devices with high efficiency and low emission. However, these devices such as fuel cells come with their shortcomings and challenges of meeting lifetime and availability goals, especially when operated outside their safe operational range. Therefore, the need to develop not just good controls but also intelligent controls arise to help respect these constraints while meeting up with the load demands. In this paper, Neural Networks (NN s) were used as a system identifier to model the dynamics of a solid-oxide fuel cell (SOFC) stack to be used in the controller design. The proposed NN model was validated by comparing its results with that of an already validated mathematical model.