This PhD is co-funded by the EPSRC Industrial CASE 2018 and BAE Systems. The PhD involves applied research within the context of defence marine industry and it will involve multi-disciplinary work in information systems, systems engineering, forecasting, modelling and simulation, maintenance, through-life engineering, software engineering. The research will extend the work on digital twins by developing algorithms that collects, analysis and distributes information for optimised efficiency and effectiveness in delivering through-life support solutions for complex engineered products such as ships and submarines. Read more Read less

The development of computer modelling, simulations and connectivity between products and a digital twin (DT) introduces new and unique opportunities to elicit value for service and support through optimised decision making. The opportunities, risks and requirements of a digital twin are not fully understood in research literature, which makes this proposal relevant for further academic research. The key challenge and most significant benefit of the DT is realised by the combination, integration and analysis of data sources from across the product lifecycle and across difference levels from component to system of systems.

A Digital Twin (DT) could be used for predicting how a physical product behaves and performs in the future in a range of alternative scenarios and environments. The research fundamental for this PhD centres on developing the algorithms that will allow creation of the digital representation of the physical asset for a large variety of dynamic scenarios (e.g. operating conditions, maintenance interventions) within a maintenance context. The DT could be used to determine when and where failure or damage is likely to occur, and when to perform maintenance. Any unanticipated failures or damage found will be added to the integrated DT so that the model continually reflects the current state of the actual platform or engine.

The Through-life Engineering Services (TES) Centre focuses on developing knowledge, technology and process demonstrators to provide the capability for the concept design of high-value engineering systems based on design and manufacturing for through-life engineering services. The TES Centre has critical mass of researchers in augmented reality, digital twins, degradation assessment and artificial intelligence. The TES Centre has currently several research contracts in the areas related to the post and providing excellent reputation at the national and the international level.

A major focus of this PhD will be on developing a role for the use of a DT at the commodity level for planning maintenance, repair, overhaul and update (MROU). This will aim to support with defining what maintenance intervention needs to be conducted in the front end to be able to meet the vision for MROU with the aim of improving the through-life costs and performance. This PhD aims to develop algorithms to operate a digital twin that fully integrates the computational representation of a commodity through rapid simulation and visualisation within a maintenance context. The academic contribution is in developing an Artificial Intelligence (AI) enabled digital twin that allows data integration and simulation for scientifically evaluating varied maintenance interventions. The project will target to fulfil the following objectives:

• Identify the major maintenance challenges and prioritise opportunities to implement a DT for planning MROU. This will rely on industry wide engagement to understand the maintenance scenarios. 

• Development of a dynamic data environment. This involves developing a computational environment to combine, and interrogate large scale data from multiple sources across different timespans. This objective involves developing an autonomous data system that evolves in real time. This will be designed to allow the data to flow through to the integrated modelling and simulation using both analytical and numerical methods.

• Developing fly forward simulation determining the impact of future maintenance scenarios. Develop an AI platform for high fidelity modelling and simulation to learn from current and historical maintenance data and build a quantitative representation of the impact of future maintenance interventions. Once a prototype has been developed, the research will test the degree of accuracy between the real life for alternative conditions and operations.   

• Developing a model installed to DT to predict current and future conditions. Explore and apply visualisation approaches (including 3D representation) for the DT across the maintenance life cycle. This will involve building a visualisation platform for multi-dimensional data and modelling outputs

This project involves applied research with BAE Systems. The student will be based at Cranfield campus at Cranfield University, with regular visits to BAE systems at Portsmouth. The student will be expected to travel to other sites of BAE and/ or other organisations as required.

The student will use the cutting edge Advanced Visualisation Lab in the Through-life Engineering Services Centre at Cranfield to develop the Digital twin. The DT concept is applicable to all BAE Business Units and can offer new and brave applications in:
1) Tailored maintenance delivered specific to a component serial number.
2) Better informed decision making capability in the design stage to future-proof the implications of proactive maintenance actions.
3) Just in Time (JIT) spares provisioning from the supplier reducing customer requirements to warehouse and administer spares, and reduced maintenance burden on spares with a ‘shelf life’.
4) Potential to reduce costly range of test equipment, user manuals, spares, calibration requirements, and facilities.

The student will have funding to attend international conferences and go on training where relevant. The student will gain skills in: applied research, digital twins, software engineering, modelling, simulation, maintenance, through-life engineering, degradation assessment, project management, and presentation skills. 


At a glance

  • Application deadline30 Nov 2018
  • Award type(s)PhD
  • Duration of award3 years
  • EligibilityUK
  • Reference numberSATM0083

Entry requirements

Applicants should have a first or second class UK honours degree or equivalent in a related discipline such as computer science, mechanical engineering, electrical and electronic engineering, and industrial engineering.

Funding

To be eligible for this funding, applicants must be a UK national. We require that applicants are under no restrictions regarding how long they can stay in the UK i.e. have no visa restrictions or applicant has “settled status” and has been “ordinarily resident” in the UK for 3 years prior to start of studies and has not been residing in the UK wholly or mainly for the purpose of full-time education. (This does not apply to UK or EU nationals). Due to funding restrictions all EU nationals are eligible to receive a fees-only award if they do not have “settled status” in the UK. The funding amount is between £17k-£20k p/a tax free.


About the sponsor

Sponsored by EPSRC Industrial CASE 2018, BAE Systems and Cranfield University.

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, identify opportunities for collaboration and create smaller communities of practice.  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

If you are eligible to apply for this research studentship, please complete the online application form.

For further information please contact Dr. John Erkoyuncu
T: 44 (0)1234 754717
E: j.a.erkoyuncu@cranfield.ac.uk