Prof. Ghanim Putrus, Northumbria University, UK
Ghanim Putrus is Emeritus Professor at the Department of Engineering, Physics and Mathematics, Northumbria University, Newcastle upon Tyne, UK. He has over 40 years of research experience in Electrical Engineering with over 230 publications, including one patent, 5 book chapters and neuromas invited talks at national and international events. He has led several research projects (funded by EU, EPSRC, Innovate UK and industry) and has often provided consultancy for industry in the area of energy and electrical power engineering, with focus on the integration of renewable energy generation and electric transport. Professor Putrus is Visiting Professor at the China-EU Institute for Clean and Renewable Energy (ICARE), Huazhong University of Science & Technology, Wuhan, China, 2011-to-date. He is also Associate Editor for Elsevier Renewable Energy journal and serves on the editorial board for the World Electric Vehicle Journal and Energies journal in addition to the technical/steering committees for several international conferences. He has been actively involved in the Institution of Engineering Technology (IET) and has organised several conferences and professional events. He was Chairman of the IET Northumbria Network (2004/2005) and served on the executive committee of the IET Power Trading and Control Professional Network (2001-2010). Main research interests are application of power electronics in power systems, renewable energy systems, electric vehicles and their integration into the electricity grid (smart grids).
Speech Title: Can we maintain sustainable, secure and affordable energy and transport systems?
Abstract: Electrical power and transport systems evolved throughout the past century to provide adequate electricity supply and transport that our civilization now rely on. Given the concerns about the security of energy supply and climate change, the challenge now is how to maintain sustainable, reliable and affordable energy and transport systems. Renewable energy generation and electric transport are seen as the way forward to provide sustainable green energy and transport systems. However, the integration of these two systems is not without challenges. This talk will give an overview of the challenges due to increased deployment of renewable energy sources and electric vehicles and the need for a smart integration of the two systems together with the electricity grid. It will also cover opportunities that emerging technologies provide not only to meet these challenges but also to foster new operational and business models that will help maintain reliable and affordable electricity and transport systems as well as improve their efficiency and lower their environmental impacts.
Prof. Belkacem Ouldbouamama, University of Lille, France
Bio: Belkacem OULD BOUAMAMA is full Professor in automatic control at Graduate School of Engineering Polytech Lille (France), where he has been Director of the Research for 15 years. He is in charge of a diagnosis and prognosis research team at the CRIStAL laboratory of the National Center for Scientific Research (CRIStAL, CNRS) in Lille, where his research activities concern Integrated Design for Supervision of System Engineering based on Bond Graph theory. Their industrial applications are mainly, renewable energies and green hydrogen. He has authored and co-authored more 65 peer-reviewed journals, 180 conference papers and 20 books and book chapters. He has given more than 20 invited talks and tutorials and keynotes around the globe. More details are given in https://pro.univ-lille.fr/belkacem-ould-bouamama/
Speech Title: Hybrid Bond Graph-Convolutional Neural Network (BG-CNN) for online diagnosis”
Abstract: In recent years, there has been a lot of interest in Fault Detection and Isolation (FDI) for systems. Model-based methods and Machine Learning (ML)-based approaches have been extensively developed to detect and identify specific faults by taking into consideration, respectively, the mathematical description of the monitored process and the statistical model constructed from historical data. The current data-driven FDI techniques generally emphasize accuracy and rarely draw attention to the lack of readily accessible labeled data in the industry. This conference aims to develop a hybrid fault diagnosis method by combining the well-established graphical technique of Bond-Graph (BG) with the powerful pattern recognition ability of Convolutional Neural Network (CNN) to improve the overall fault isolation performance. A new formalism named BG-CNN method is proposed, which can utilize the residuals generated from the BG model in a CNN for improved fault isolation with a minimal number of labeled data.