Research Fellow in Machine Learning-enabled Optimisation of Cryogenic Machining Processes

 
Published
WorkplaceLeeds, Yorkshire, UK
Category
Position
Skip to main content

  • Home
  • Login
  • Register


View All Vacancies Research Fellow in Machine Learning-enabled Optimisation of Cryogenic Machining Processes Do you want to join a multidisciplinary team of world-leading experts developing enhanced industrial machining processes of the future? Do you want to bring expertise in Machine Learning and Optimisation to assess sustainability goals of industrial processes? Currently the dominant approach for cooling and lubricating machining processes, such as drilling, milling and turning, is to use emulsion-based coolants (otherwise known as metalworking fluids) at high flow rates. There are many serious environmental, financial and health and safety reasons for reducing industry's reliance on emulsion coolants - an estimated 320,000 tonnes/year in the EU alone, up to 17% of total production costs, and over 1 million people are exposed regularly to the injurious effects of its additives which can cause skin irritation and even cancers. Serious environmental problems are also caused by the up to 30% of coolant that is lost in leaks and cleaning processes and which eventually ends up polluting rivers.

These issues have motivated extensive research efforts to identify more sustainable machining processes. There is growing and compelling evidence from preliminary studies that cryogenic machining with supercritical CO2 (scCO2) with small amounts of lubricant (Minimum Quantity Lubrication, MQL, referred to as scCO2+MQL machining) can provide a high-performing and more sustainable alternative. Current knowledge gaps in the relationships between key input and output variables, the reasons for variations in performance and concerns over the release of CO2, are preventing a major uptake of this technology by UK manufacturers.

You will take the lead in developing Machine Learning and Optimisation methods to maximise the engineering performance of this advanced machining process, accounting for environmental sustainability and economic factors and using unique data-sets generated from state-of-the-art experimental investigations at Leeds and machining trials at the AMRC. The role will see you analysing the fundamental heat transfer mechanisms during machining with supercritical CO2 and Minimum Quantity Lubrication, developing economic and sustainability models of potential CO2 re-capture methods and developing Machine Learning methods to map and predict the relationships between the key input and output performance variables. You will develop user-friendly software tools in Python, which will enable academic and industry stakeholders to use the outcomes of your research and present your research at key academic and industry meetings, in the UK and overseas.

You will work with a second postdoctoral researcher and with an integrated academic and industrial project team to develop new learning and to disseminate the project findings via publications and presentations.

To explore the post further or for any queries you may have, please contact:

Harvey Thompson , Professor of Computational Fluid Dynamics

Tel: +44 (0)113 343 2136 or email: H.M.Thompsonleeds.ac.uk

Due to funding restrictions, an appointment will not be made higher than £37,467 p.a.

In your application, please refer to myScience.uk and reference JobID 205199.