Osinachi Victor Chukwujama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Osinachi Victor Chukwujama has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Ogheneruemu Nathaniel Akatakpo
Department of Computer Science, University of Benin, Benin City, Nigeria
2 shared publications - Ololade Funke Olaitan
The University of Utah
2 shared publications - Adedapo Olosunde
The University of Toledo
1 shared publication - Azeez Abiodun Ajibola
Baze University Department of Accounting and Finance
1 shared publication - Chukwuemeka George Ochieze
Department of Mechanical and Aerospace Engineering, University of Virginia, Charlottesville, VA 22903, USA
1 shared publication Chukwumaeziokwu James Emejulu
1 shared publication
Latest Publications
- Open Access
- 27 April 2026
- Published by PT. Teknologi Futuristik Indonesia in Scientific Journal of Engineering Research
- Vol. 2 (3) , 339-365
AI-Assisted Design and Control of Smart Electromechanical Devices for Energy-Efficient Applications
The growing global demand for sustainable energy has elevated the importance of energy-efficient electromechanical systems in applications such as electric vehicles (EVs), renewable energy conversion, and industrial automation. These systems reduce carbon emissions and operational costs by optimizing power use, aligning with UN Sustainable Development Goals and 2050 net-zero targets. However, traditional control methods like field-oriented control (FOC) and PID controllers struggle with nonlinear dynamics, parameter variations, and variable loads, resulting in suboptimal performance, higher energy losses, and reduced robustness. This paper addresses this gap by proposing an AI-assisted framework for designing and controlling smart electromechanical devices, using permanent magnet synchronous motor (PMSM) drives as a prototype. The approach integrates adaptive neural networks with reinforcement learning to enable real-time optimization of dynamic response, robustness, and energy efficiency. The system was rigorously simulated in MATLAB/Simulink using a d-q reference frame model under nominal, disturbed, and variable-load conditions. Results show significant improvements: transient settling time reduced by 42–58%, overshoot by 60–67%, and energy consumption by 12–18%, achieved through minimized torque ripple and losses. The framework also demonstrated superior disturbance rejection and parameter-variation stability. These advances position the proposed solution as a transformative approach for sustainable applications, enhancing efficiency in EV propulsion, renewable energy integration, and industrial automation, while paving the way for future hardware implementation and scalable AI-driven systems.
- 27 April 2026
- Published by PT. Teknologi Futuristik Indonesia in Scientific Journal of Engineering Research
- Vol. 2 (3) , 339-365
Open AccessAI-Assisted Design and Control of Smart Electromechanical Devices for Energy-Efficient Applications
The growing global demand for sustainable energy has elevated the importance of energy-efficient electromechanical systems in applications such as electric vehicles (EVs), renewable energy conversion, and industrial automation. These systems reduce carbon emissions and operational costs by optimizing power use, aligning with UN Sustainable Development Goals and 2050 net-zero targets. However, traditional control methods like field-oriented control (FOC) and PID controllers struggle with nonlinear dynamics, parameter variations, and variable loads, resulting in suboptimal performance, higher energy losses, and reduced robustness. This paper addresses this gap by proposing an AI-assisted framework for designing and controlling smart electromechanical devices, using permanent magnet synchronous motor (PMSM) drives as a prototype. The approach integrates adaptive neural networks with reinforcement learning to enable real-time optimization of dynamic response, robustness, and energy efficiency. The system was rigorously simulated in MATLAB/Simulink using a d-q reference frame model under nominal, disturbed, and variable-load conditions. Results show significant improvements: transient settling time reduced by 42–58%, overshoot by 60–67%, and energy consumption by 12–18%, achieved through minimized torque ripple and losses. The framework also demonstrated superior disturbance rejection and parameter-variation stability. These advances position the proposed solution as a transformative approach for sustainable applications, enhancing efficiency in EV propulsion, renewable energy integration, and industrial automation, while paving the way for future hardware implementation and scalable AI-driven systems.
- Open Access
- 31 May 2025
- Published by Publishing Center Dialog in Path of Science
- Vol. 11 (5) , 7001-7009
Quantum Computing in Artificial Intelligence: a Review of Quantum Machine Learning Algorithms
Two of the most disruptive technologies of the 21st century are quantum computing and artificial intelligence. Their intersection has led to the emergence of a new discipline referred to as Quantum Machine Learning (QML), which aims to enhance the capabilities of classical machine learning by leveraging the computational advantages of quantum devices. This paper provides a survey of the most advanced Quantum Machine Learning (QML) algorithms, including Quantum Support Vector Machines (QSVMs), Quantum k-nearest Neighbours (QkNN), Quantum Principal Component Analysis (QPCA), Quantum Neural Networks (QNNs), and Quantum Reinforcement Learning (QRL). The theoretical and practical status, as well as the empirical performance, of these algorithms, were summarised using a structured review method. The findings reveal a potential for speed-ups in classification, clustering, and optimisation among a range of applications, particularly for perfect quantum systems. However, hardware constraints, software irregularities, and training issues, such as barren plateaus, have limited the practical utility of this approach. Applications of QML in areas such as disaster preparedness and management, drug discovery, environmental sustainability, urban planning methodology, NLP, and finance demonstrate both the potential and current limitations of QML, with most applications still at the proof-of-concept level. In this review, we conclude that QML could be revolutionary, but its feasibility ultimately relies on improvements in physical hardware, the robustness of algorithms, and the standardisation of benchmarks.
- 31 May 2025
- Published by Publishing Center Dialog in Path of Science
- Vol. 11 (5) , 7001-7009
Open AccessQuantum Computing in Artificial Intelligence: a Review of Quantum Machine Learning Algorithms
Two of the most disruptive technologies of the 21st century are quantum computing and artificial intelligence. Their intersection has led to the emergence of a new discipline referred to as Quantum Machine Learning (QML), which aims to enhance the capabilities of classical machine learning by leveraging the computational advantages of quantum devices. This paper provides a survey of the most advanced Quantum Machine Learning (QML) algorithms, including Quantum Support Vector Machines (QSVMs), Quantum k-nearest Neighbours (QkNN), Quantum Principal Component Analysis (QPCA), Quantum Neural Networks (QNNs), and Quantum Reinforcement Learning (QRL). The theoretical and practical status, as well as the empirical performance, of these algorithms, were summarised using a structured review method. The findings reveal a potential for speed-ups in classification, clustering, and optimisation among a range of applications, particularly for perfect quantum systems. However, hardware constraints, software irregularities, and training issues, such as barren plateaus, have limited the practical utility of this approach. Applications of QML in areas such as disaster preparedness and management, drug discovery, environmental sustainability, urban planning methodology, NLP, and finance demonstrate both the potential and current limitations of QML, with most applications still at the proof-of-concept level. In this review, we conclude that QML could be revolutionary, but its feasibility ultimately relies on improvements in physical hardware, the robustness of algorithms, and the standardisation of benchmarks.
- 28 May 2025
- Published by Sciencedomain International in Journal of Engineering Research and Reports
- Vol. 27 (6) , 331-344
Secure and Resilient Industrial IoT Architectures for Smart Manufacturing: A Comprehensive Review
Smart manufacturing, driven by the Industrial Internet of Things (IIoT), is transforming real-time data sharing, predictive maintenance, and process automation. However, the increasing complexity and connectivity of IIoT environments present significant security and resilience challenges that threaten operational safety, data integrity, and business continuity. This paper presents a comprehensive review of secure and resilient architectures for IIoT in smart manufacturing, highlighting the interaction between enabling technologies (e.g., edge computing, AI/ML, blockchain) and emerging threats in the cyber-physical environment. We explore vulnerabilities and attack surfaces and examine resilience strategies such as redundancy, fault tolerance, and self-healing capabilities that ensure ongoing operations despite disruptions. Key standards and best practices, including ISA/IEC 62443 and NIST frameworks, are evaluated for their effectiveness and limitations. Emerging trends—such as AI-driven proactive security, cyber-physical systems convergence, and green security initiatives—are discussed alongside open challenges and trade-offs in IIoT environments. Our analysis underscores the need for holistic, adaptive, and industry-specific solutions to enable secure and resilient IIoT architectures that foster innovation, productivity, and safety in the era of digital and connected factories.
- 28 May 2025
- Published by Sciencedomain International in Journal of Engineering Research and Reports
- Vol. 27 (6) , 331-344
Secure and Resilient Industrial IoT Architectures for Smart Manufacturing: A Comprehensive Review
Smart manufacturing, driven by the Industrial Internet of Things (IIoT), is transforming real-time data sharing, predictive maintenance, and process automation. However, the increasing complexity and connectivity of IIoT environments present significant security and resilience challenges that threaten operational safety, data integrity, and business continuity. This paper presents a comprehensive review of secure and resilient architectures for IIoT in smart manufacturing, highlighting the interaction between enabling technologies (e.g., edge computing, AI/ML, blockchain) and emerging threats in the cyber-physical environment. We explore vulnerabilities and attack surfaces and examine resilience strategies such as redundancy, fault tolerance, and self-healing capabilities that ensure ongoing operations despite disruptions. Key standards and best practices, including ISA/IEC 62443 and NIST frameworks, are evaluated for their effectiveness and limitations. Emerging trends—such as AI-driven proactive security, cyber-physical systems convergence, and green security initiatives—are discussed alongside open challenges and trade-offs in IIoT environments. Our analysis underscores the need for holistic, adaptive, and industry-specific solutions to enable secure and resilient IIoT architectures that foster innovation, productivity, and safety in the era of digital and connected factories.