Computer Science/Mechanical Engineering: Fully Funded Tata Steel PhD Scholarship: Industrial AI: Fusing Remote Sensors and Digital Modelling to Create a Smart and Sustainable Hot Strip Mill
Funding providers: Tata Steel, Swansea University
Subject areas: Industrial AI/ Material Modelling
Project start date: 1 April 2022 (Enrolment open from mid–March)
Academic supervisor: Dr C Giannetti and Professor C Pleydell-Pearce
Industrial supervisor: Mr T Baynes
Aligned programme of study: PhD in Mechanical Engineering
Mode of study: Full-time
Project description:
The steel industry produces in excess of 1.7bn tonnes of steel per year and accounts for ~10% of global carbon emissions. Digitalization of industrial processes, driven by development of low-cost wireless remote sensors and advances in data analytics, offer tremendous opportunities to improve both energy and material efficiency for the steel industry and, hence, reducing the environmental impact.
This research project will look at the application of novel sensors technologies, fused with physics informed AI models, in the hot strip mill at Port Talbot to create actionable insight during manufacture which will enable the production of tailorable, guaranteed, right-first-time materials. The research will be undertaken collaboratively with the industry partner to inform/improve management decision making to improve the hot strip mill.
The key driver for this project is to improve both energy and material efficiency for the industry both of which will help to reduce the environmental impact of the process, a 1% material efficiency saving is the equivalent of 60,000 tonnes of CO₂ saved.
The PhD Researcher will be affiliated to the M2A (Materials and Manufacturing Academy) research community and be part of the Industrial AI and Data Modelling research group, based in the Faculty of Science and Engineering at Swansea University. They will work in connection to the Made Smarter Innovation – Materials Made Smarter Research Centre, a partnership of five UK leading universities (The Universities of Sheffield, UCL, Cambridge, Brunel, Nottingham and Swansea).
The main aims of the research project are:
- Integrate these new data streams with existing hot mill data;
- Use various data analytics techniques combined with physical modelling to translate the data into useful information;
- Work with the industry partner to understand the hot rolling process and in negotiating existing IT infrastructure on the plant.