Dr Mahmoud Dhimish
Mahmoud completed his MSc in Electronics and Communications Engineering and PhD degree in Renewable Energy at the University of Huddersfield, UK. During his MSc and PhD studies, he used artificial intelligence (AI) techniques to detect faults and defects in photovoltaic (PV) systems. He applied his research to a broader renewable energy sector, e.g. wind turbines. He has developed a new photovoltaics laboratory and is a currently working as an assistant professor at the University of York since September 2021. If he is not in the lab, you'll find Mahmoud swimming at the beach or hanging out with his wife and his son and daughter, Sam and Emily.
Mahmoud also serves as the engineering training lead in the CDT (Center for Doctoral Training) Sustainable Materials for Net Zero. This prestigious position allows him to contribute his expertise and leadership in the field of engineering, specifically focusing on sustainable materials for achieving net-zero emissions. Mahmoud plays a crucial role in training and mentoring aspiring engineers, guiding them towards innovative solutions in the pursuit of a sustainable and environmentally friendly future.
Dr Dhimish serves as a member of the editorial team for the renowned Renewable Energy Journal, and Clean Energy published by Oxford University Press. Dr. Dhimish has a strong publication record with over 70 papers in prestigious scientific journals and an H-index of 26. In October 2022, he appeared in the top five of a leading index of UK scientific academics, and awarded multiple research grants (>£500k). As the PI of the EPSRC IAA, he established the UK's first vertical bifacial solar system.
June 2019 - September 2019: Research Assistant, AL SUWAIDI FTS CONSTRUCTION, Dubai, UAE. Project Title: Degradation Estimation Tool for Large-Scale Photovoltaic Systems.
September 2018 – March 2019: Research Assistant, A-SAFE, Halifax, UK. Project Title: Indoor Real-Time Positioning of Ultra-Wideband (UWB) System.
December 2017 - April 2018: Postdoctoral Research Fellow, School of Computing and Engineering, University of Huddersfield, UK. Project Title: Design and Development of AI-Based Electronics for Medical Devices
January 2016 - December 2016: Research Assistant, Faculty of Engineering and Physical Sciences, University of Leeds, UK. Project Title: Photovoltaic Multiple Configuration Assessment, Modelling, and Design.
Ghadeer Badran, a highly skilled research trainee at the Laboratory of Photovoltaics, plays a crucial role in driving our research and development efforts. With a strong background in AI and ML, Ghadeer leads the development of AI tools in the cutting-edge EPSRC IAA project titled "Next-Generation Vertically Mounted Bifacial Solar Panels: Conceptualisation, Field Testing, and Energy Performance Monitoring."
In this project, Ghadeer spearheads the conceptualization and implementation of advanced AI algorithms and ML models tailored specifically for vertically mounted bifacial solar panels. By leveraging Ghadeer's expertise, we aim to optimize the energy generation and performance of this innovative PV technology. Ghadeer's work involves developing intelligent algorithms that enable accurate modeling and simulation of vertically mounted bifacial solar panels in various environmental conditions. Furthermore, Ghadeer is actively involved in coordinating and overseeing field testing activities, ensuring the seamless integration of AI tools for real-time data analysis and energy performance monitoring. The objective is to gain valuable insights into the behavior and efficiency of these next-generation solar panels in real-world scenarios. Ghadeer's contributions significantly contribute to the project's success in unlocking the full potential of vertically mounted bifacial solar panels and enhancing their overall energy generation capabilities.
Sharmarke Mohamed Hassan
Sharmarke Mohamed Hassan, a dedicated and driven PhD student at the Laboratory of Photovoltaics, is actively engaged in a pioneering research project titled "Practical Experimentation on the Deployment of Solar Roads." This project is focused on testing and evaluating various solar cell technologies for their suitability in the deployment of solar roads. Sharmarke's research project encompasses an in-depth study of the degradation, durability, safety, and reliability mechanisms associated with these solar cell technologies in real-world conditions.
Sharmarke's work involves conducting comprehensive experiments to assess the performance and resilience of different solar cell technologies when subjected to the challenging environment of a solar road. By analyzing the degradation patterns and understanding the underlying mechanisms, Sharmarke aims to identify potential improvements in the design, materials, and manufacturing processes to enhance the overall performance and longevity of solar roads.
In addition to the practical experimentation, Sharmarke's research integrates the power of machine learning models. By applying different machine learning algorithms, he aims to develop intelligent systems capable of learning from vast amounts of data collected during the deployment and operation of solar roads. These machine learning models play a critical role in pattern recognition, fault classification, and detection associated with the developed technology. By leveraging the power of machine learning, Sharmarke seeks to enhance the efficiency and effectiveness of fault detection mechanisms, enabling timely interventions and maintenance, thereby maximizing the safety and reliability of solar road systems.
Sharmarke's research project highlights the interdisciplinary nature of his work, requiring expertise in photovoltaics, material science, civil engineering, and machine learning. Through collaboration with experts in these fields, Sharmarke aims to bridge the gap between theory and practical implementation, facilitating the widespread adoption of solar roads as a sustainable and energy-efficient infrastructure solution.
Aktouf Lotfi, an accomplished and diligent PhD student at the Laboratory of Photovoltaics, is actively engaged in an exciting research project titled "Development of Genetic Algorithms and Bayesian Networks for PV Fault Classification." This project focuses on the development of an intelligent fault classification system for photovoltaic (PV) panels, leveraging the power of genetic algorithms and Bayesian networks.
Aktouf's research project aims to address the critical challenge of identifying and classifying faults in PV panels accurately. By utilizing genetic algorithms, Aktouf aims to optimize the fault classification process by evolving and refining a set of rules or parameters that can effectively distinguish between different types of faults. The genetic algorithms will iteratively evolve and improve the classification models based on the analysis of available data, maximizing the accuracy and efficiency of fault detection.
Additionally, Aktouf incorporates Bayesian networks into the fault classification system. Bayesian networks provide a probabilistic framework for modeling and reasoning under uncertainty. By integrating historical data, sensor readings, and expert knowledge into a Bayesian network structure, Aktouf's research project aims to create a comprehensive diagnostic system that can assess the likelihood of specific faults based on observed symptoms and provide accurate diagnostic information to the maintenance team.
The fault classification system developed by Aktouf will rely on data collected from sensors installed in PV panels. These sensors will monitor various parameters such as voltage, current, temperature, and other relevant metrics, providing valuable information for fault detection and classification. By analyzing these sensor data using the genetic algorithms and Bayesian networks, the system will be able to identify and classify faults, enabling prompt maintenance and minimizing downtime.
Aktouf's research project emphasizes the importance of accurate fault classification in the maintenance and performance optimization of PV panels. By providing the maintenance team with precise diagnostic information, the system developed by Aktouf will enable timely interventions and facilitate efficient troubleshooting processes. This, in turn, will enhance the overall reliability and performance of PV systems, leading to improved energy production and reduced costs.
Dr Olufemi Olayiwola
Dr Olufemi, an esteemed associate member of the Laboratory of Photovoltaics since 2023, brings invaluable expertise to the research and development activities within the lab. His current focus revolves around harnessing the power of Artificial Intelligence (AI) for photovoltaic (PV) diagnostics, monitoring, and the development of fault tolerance algorithms.
In his role, Olufemi plays a vital role in advancing the field of PV diagnostics by integrating AI techniques into the analysis and interpretation of PV system data. By leveraging machine learning algorithms and deep neural networks, Olufemi aims to develop intelligent models capable of accurately identifying and diagnosing various issues and anomalies in PV systems. This includes the detection of performance degradation, component faults, shading effects, and other operational challenges that may affect the overall efficiency and reliability of PV installations.
Furthermore, Olufemi's research also focuses on the development of advanced monitoring systems that leverage AI for real-time data analysis. By continuously analyzing and interpreting data collected from sensors, weather stations, and other monitoring devices, Olufemi aims to provide valuable insights into the performance and health of PV systems. These insights will facilitate proactive maintenance, optimize system performance, and ensure efficient energy generation.
In addition to his role at the Laboratory of Photovoltaics, Olufemi holds a prestigious research fellowship position at the Institute of Safe Autonomy, located at the University of York. This affiliation enables Olufemi to collaborate with experts in the field of autonomous systems, robotics, and AI, fostering interdisciplinary research and innovation. Through this collaboration, Olufemi seeks to explore synergies between the fields of safe autonomy and photovoltaics, with a particular focus on developing fault tolerance algorithms for PV systems. These algorithms aim to enhance the resilience and reliability of PV installations, enabling them to operate efficiently and safely in various environmental conditions and unforeseen circumstances.
Dr Tochukwu Emma-Duru (Currently working as Assistant Professor in University of Lagos, Nigeria)
Dr Muhammad Hussaian (Currently working as Assistant Professor at the University of Huddersfield, UK)
Dr Ali Mohd Ali (Currently working as Assistant Professor at the University of Jordan, Jordan)
MSc by Research:
Mr Ahmad Mohsen (Working as sales manager at Netflix, UK)
Mr Waqas Mohammed (Working as University Technician at the University of Bristol, UK)
Mr Spencer Gittens (Working as engineering AI lead at Red Bull, UK)
Mr Grogba Joule (Working as software engineer at Eskom, South Africa)