Overview

Data-driven in-process sensing is a need from the food industry to deliver sustainable, safe and productive current and future food manufacturing systems. Dr Nicholas Watson leads a research group focussing on this output and will share his group's activities alongside a deep dive into a machine learning problem from his colleague Dr Alexander Bowler.

Speakers

Dr Nicholas Watson, Associate Professor, University of Nottingham

Nik is a Chartered Engineer with a MEng in Mechanical Engineering (University of Hull, 2006) and PhD in Chemical Engineering (University of Leeds, 2010). Nik Joined the University of Nottingham in 2014 and is an Associate Professor of Chemical Engineering. Since joining the University of Nottingham Nik has published over 50 journal articles and led projects funded by Innovate UK, EPSRC, STFC and the Royal Academy of Engineering. Nik is currently the deputy director of the Horizon Centre for Doctoral Training and on the Food Standards Agency register of Experts. Nik's research is primarily focussed on data-driven in-process sensing to deliver sustainable, safe and productive current and future food manufacturing systems. Data-driven sensing combines cost-effective in-process sensors (e.g. optical and ultrasonic) with machine learning techniques and overcomes many of the challenges associated with utilising sensors to produce actionable information to monitor processes (e.g. mixing, cleaning and fermentation) and materials (e.g. online quality and safety inspection) within challenging manufacturing environments. Nik has broader expertise and research interests in Digital Manufacturing within the food and drink sector with projects exploring the use of data and digital technologies including robotics and the Industrial Internet of Things.

Dr Alexander Bowler, Research Assistant, University of Nottingham

Alex completed his MEng in 2018 and recently defended his PhD thesis in 2022, both in Chemical Engineering at the University of Nottingham. His PhD thesis was titled "Ultrasonic measurements and machine learning methods to monitor industrial processes". The focus of this thesis was on developing a machine learning pipeline as well as transfer learning and domain adaptation methods for process monitoring using ultrasonic sensors. Alex has also published research articles on topics such as near-infrared spectroscopy for allergen classification in food powders and commodity price forecasting for techno-economic analyses. Currently, Alex is a research assistant on the EATS (Enhancing Agri-Food Transparent Sustainability) EPSRC funded project. As part of this project, he is investigating open-source carbon footprint calculations, Bayesian optimisation of brewery processes, and real-time process optimisation using sensor measurements. In addition, Alex is also undertaking a placement with a company to develop domain adaptation methods for colour sensors.

The material presented in this webinar has not been peer-reviewed. Any opinions are the presenters' own and do not necessarily represent those of IChemE or the Food & Drink Special Interest Group. The information is given in good faith but without any liability on the part of IChemE.

Webinar archive

This webinar is free of charge and open to all to attend, but if you wish to access the slides and a recording to replay on demand then you will need to be a member of the Food and Drink Special Interest Group.