ACS-02-Ward – Application of Machine Learning, Data-Science and Digital Twins in Aerospace Manufacturing

Details

Digital twins have emerged as a new technology offering the potential to revolutionise the aerospace industry. These virtual replicas of physical assets hold the key to optimising high-value manufacturing processes, such as manufacturing jet engine turbine blades. However, the task of creating accurate digital twins for Computer Numerical Control (CNC) machines, which play a pivotal role in advanced manufacturing in the aerospace industry, presents a formidable challenge. This challenge is rooted in the ability to access data. Within high value manufacturing, accessing real-time data from CNC machines to create accurate digital twins is essential, however, it can be prohibitively expensive (paywalled by equipment manufacturers) or challenging due to legacy equipment and poor data rates. This can lead to data poverty.

Data poverty is where companies without access to critical data will find it difficult to compete with others that are using data-driven insights to optimise their operations and as factories become smarter and more digitalised, this will only increase. Is it possible to make better use of the data available in a networked factory? For example, if some machines have better data access than others? Is it possible machines could learn from each other to infer the performance and behaviour of other machines? and support the digital twins for accurate predictions?

In direct response to these questions, this project which lies at the intersection between academia and industry, will develop innovative research underpinned by the application of a deep learning method known as transfer learning. Through this approach, a collaborative learning environment is developed among interconnected CNC machines within industrial settings. The ultimate outcome, directly addressing data poverty, is a step change in digital twin accuracy and robustness, which will support industrial digital tools and address the productivity challenges the UK’s industrial sector faces.

The project is a special collaboration, combining the world leading research in machine learning, signal processing and advanced control at the department of Automatic Control and Systems Engineering (ACSE) with the internationally renowned translational research facilities at the University of Sheffield Advanced Manufacturing Research Centre (AMRC). The project will require the candidate to develop skills in data-driven techniques and machine learning, signal processing, hands-on and practical sensorisation and experimental skills, advanced manufacturing, entrepreneurship and commercialisation skills, and the ability to interact with academics and industrialists alike.

The project will make full use of the state-of-the-art facilities at the AMRC and the candidate can expect to spend their time between the University of Sheffield’s main campus and the AMRC.

The supervision team consists of Dr Rob Ward, a specialist in digital manufacturing who holds a joint position between the AMRC and ACSE and Dr Mahnaz Arvaneh, a senior lecturer in brain-computer interfaces and machine learning at ACSE.

The candidate can expect to be developing industrially-focused academic research at the intersection of machine learning and aerospace manufacturing. The project will provide exposure to and perfectly align future career prospects with major international companies such as Rolls-Royce, Boeing, Airbus, Siemens and many more. The successful candidate will graduate with advanced technical skills and be primed for future leadership positions in tomorrow’s data-driven industrial workplace.

Ideally the candidate will have a background in engineering and have an active interest in AI, machine learning and data-science.

Interested candidates are strongly encouraged to contact Dr Rob Ward to discuss your interest in and suitability for the project prior to submitting your application.

Please refer to the EPSRC DTP webpage for detailed information about the EPSRC DTP and how to apply.

Application Form

This is a funded PhD studentship. The award will fund the full (UK or Overseas) tuition fee and UKRI stipend (currently £18,622 per annum) for 3.5 years, as well as a research grant to support costs associated with the project.