From MLP to LLMs - The Road to Industry 5.0
Prof. Seán McLoone
Prof. Seán McLoone
Abstract:
The advances in AI over the last 35 years, from the shallow neural networks of the 1990s to the deep learning models of the last decade, have yielded many successful applications in industry, such as soft sensing, automated inspection, predictive maintenance, and fault diagnosis. Indeed, AI has been one of the ICT technologies underpinning the transition from Industry 3.0 to Industry 4.0. It is increasingly becoming centre stage as we turn our attention towards realising the next industrial evolution/revolution (Industry 5.0) - achieving human-centric, sustainable, and resilient manufacturing enterprises.
In this talk I will provide an overview of my own journey in AI for manufacturing research towards industry 5.0, from early work on shallow neural networks for soft sensing to more recent projects on deep neural networks for predictive maintenance and fault diagnosis, and ending with ongoing research at the Centre for Intelligent Autonomous Manufacturing Systems in QUB on employing AI techniques to enable robots to learn to anticipate human motion and actions, with the view to leveraging this capability to enhance human-robot collaboration.
The advances in AI over the last 35 years, from the shallow neural networks of the 1990s to the deep learning models of the last decade, have yielded many successful applications in industry, such as soft sensing, automated inspection, predictive maintenance, and fault diagnosis. Indeed, AI has been one of the ICT technologies underpinning the transition from Industry 3.0 to Industry 4.0. It is increasingly becoming centre stage as we turn our attention towards realising the next industrial evolution/revolution (Industry 5.0) - achieving human-centric, sustainable, and resilient manufacturing enterprises.
In this talk I will provide an overview of my own journey in AI for manufacturing research towards industry 5.0, from early work on shallow neural networks for soft sensing to more recent projects on deep neural networks for predictive maintenance and fault diagnosis, and ending with ongoing research at the Centre for Intelligent Autonomous Manufacturing Systems in QUB on employing AI techniques to enable robots to learn to anticipate human motion and actions, with the view to leveraging this capability to enhance human-robot collaboration.
|
Prof. Seán McLoone is Professor of Applied Computational Intelligence and Director of the Centre for Intelligent Autonomous Manufacturing Systems (i-AMS) at Queen’s University Belfast. He is also Director of the Energy, Power and Intelligent Control (EPIC) Research Centre within the School of Electronics, Electrical Engineering and Computer Science at Queen’s University Belfast. Prof McLoone’s research interests are in computational intelligence techniques, machine learning and data analytics with applications in advanced manufacturing and power systems. His research has a strong application focus, with many projects undertaken in collaboration with industry in areas such as process monitoring, control, optimisation, time series prediction, and in-line sensor characterization. At a professional level, Prof. McLoone is a Chartered Engineer, a Fellow of the Institute of Engineering Technology (IET), and a Senior Member of the Institute of Electrical and Electronic Engineers (IEEE). He is a member of the IFAC Technical Committees on Computational Intelligence in Control (TC3.2), and Modelling, Identification and Signal Processing (TC1.1) and has previously served as Member of the Accreditation Board of Engineers Ireland and as a non-executive Director on the Board of Directors of Irish Manufacturing Research Ltd. He currently serves as an Associate Editor for the ‘Transactions of the Institute of Measurement and Control’ and as a member of the Editorial Board of ‘Engineering Applications of Artificial Intelligence’
|
