This PhD is within the context of digital twins for complex assets such as aero-engines, and turbines. Digital twins are digital representations of an asset and process, and aim to provide a comprehensive and accurate representation. However, there are often challenges with ensuring the accuracy of the digital twin. This PhD is focusing on developing a machine learning based approach for the digital twin to self-learn if there is an inaccuracy in the digital twin, and to correct the inaccuracy by bringing the digital twin to the accurate state. Read more Read less

This is a self-funded PhD position to work with Prof John Erkoyuncu in the Centre for Digital Engineering and Manufacturing. 

Background

In the maintenance repair and overhaul (MRO) industry, the maximisation of equipment availability at a minimum cost has become one of the key challenges. Therefore, it is of high importance to be effective with MRO operations. Some of the key challenges emerging are: 
-  A range of requirements to sustain availability for a variety of complex tasks on a large variety of complex systems;
- Diagnosing the equipment health status proactively with minimal resources.
- Making sure that quality requirements are achieved.

Therefore, a new way of communication and gathering data has to be found, avoiding the current issues encountered in the MRO industry. Digital twins are emerging as an enabler for these. In this age of globalisation and digitalisation, many industries have evolved from a physical space information flow towards a two-way communication between virtual and physical space. The literature is increasingly paying attention to how can a virtual system adjust itself to the constantly changing conditions of the physical space of information that influences the operation dynamics of the MRO requirements. In this process, there are still many challenges with ensuring the digital twin is accurately representative of the physical asset (E.g. plane) and/or processes (e.g. maintenance). 

This exciting PhD is aiming to create a new approach whereby the digital twin can 1) realise if there is a deviation from the accurate state of the asset and/or process, 2) understand where the difference originates, and 3) respond by making a change automatically in the digital twin, either by changing the type and amount of information needed, or by adjusting the models to increase the representability of the digital twin. We consider this process to apply concepts from resilience engineering to enhance the responsiveness of the digital twin when there are issues in the accuracy of its representation of the asset / process. 

Aim

The aim of the PhD is to develop a machine learning based simulation approach to optimise the accuracy of the digital twin representativeness of an asset/process, bearing in mind the ability to response to the inaccuracy, costs, resources, and timeliness. The machine learning will rely on data from past inaccuracies experienced in the digital twin, data mining to explore data across different projects, dynamic root cause analysis, and both tangible and expert opinion based data. 

The PhD will rely on case studies from the aerospace, defence, and wind sectors. The project will target to enhance the trust in the digital twin by its operators. Accordingly, there will be some research required to understand the implication of introducing resilience to the digital twin on the operators. This PhD will bring together a number of research themes in the fields of digital twins, data mining, AI and machine learning, optimisation and maintenance. 

Objectives

  1. Develop a data structure to support the digital twin needs 
  2. Develop an approach to self-learn if there is a deviation from accurate asset/process representation in the digital twin
  3. Develop an probabilistic risk based approach to identify where the deviation in the accuracy originates, and to automatically understand its data and model sources
  4. Develop an machine learning based approach to self-adapt the digital twin to increase its accuracy of representativeness. 
  5. Develop and validate a simulation toolkit with machine learning features to optimise the accuracy of the digital twin
  6. Apply use cases to evaluate the trust in the digital twin by introducing the resilience features. 

At Cranfield, the candidate will be based at the Centre for Digital Engineering and Manufacturing which hosts cutting-edge digital engineering facilities. The student will have access to high-end computers for simulating the complex nature of maintenance. The candidate will work on his/her research individually with supervisors and collaborates with other researchers in the field at the Centre.

 

At a glance

  • Application deadlineOngoing
  • Award type(s)PhD
  • Duration of award3 years
  • EligibilityUK, EU, Rest of World
  • Reference numberSATM0197

Entry requirements

Candidates should have a minimum of an upper second (2.1) honours degree (or equivalent) preferably in Computer Science/ Mechanical Engineering / Industrial Engineering / Mathematics / Operations Research but candidates in other degrees related to Engineering or related quantitative fields would be considered. Candidates with an MSc degree in these disciplines will be desirable.

Funding

This is a self-funded PhD; open to UK, EU and International applicants.

About the sponsor

This is a self-funded PhD that includes the ability to participate in industry-led research initiatives and access to the Cranfield Doctoral Training Network.

Cranfield Doctoral Network

Research students at Cranfield benefit from being part of a dynamic, focused and professional study environment and all become valued members of the Cranfield Doctoral Network. This network brings together both research students and staff, providing a platform for our researchers to share ideas and collaborate in a multi-disciplinary environment. It aims to encourage an effective and vibrant research culture, founded upon the diversity of activities and knowledge. A tailored programme of seminars and events, alongside our Doctoral Researchers Core Development programme (transferable skills training), provide those studying a research degree with a wealth of social and networking opportunities.


How to apply

To apply for this PhD opportunity please complete the application form using the button below. 

Apply now

For further information please contact:      

Name: Prof. John Erkoyuncu
Email: j.a.erkoyuncu@cranfield.ac.uk
T: (0) 1234 75 4717