Uncertainty-Driven Autonomy in Prognostics for Asset Health

About the RAINZ CDT

The EPSRC Centre for Doctoral Training in Robotics and Artificial Intelligence for Net Zero is a partnership between three of the UK’s leading universities (The University of Manchester, University of Glasgow and University of Oxford).

Robotics and Autonomous Systems (RAS) is an essential enabling technology for the Net Zero transition in the UK’s energy sector. However, significant technological and cultural barriers are limiting its effectiveness. Overcoming these barriers is a key target of this CDT.The CDT’s research projects will focus on how RAS can be used for the inspection, maintenance and repair of new infrastructure in renewables (wind, solar, geothermal, tidal, hydrogen) and nuclear (fission and fusion), and to support the decarbonization of existing maintenance and decommissioning of assets.

We are seeking motivated and curious graduate scientists and engineers who are interested in developing new skills and have a desire to help increase use of RAS to support the UK’s Net Zero strategy. RAINZ CDT students will play an important role in advancing this rapidly growing area of science and engineering.

All students spend the first year at The University of Manchester undertaking taught MSc studies and bespoke CDT training. Students must achieve an average of 65% or higher in their MSc assessments to be considered for progression to the PhD component of the programme.

* Note:

Students do not graduate with an MSc degree as the summer period is spent undertaking a CDT summer school rather than an MSc Dissertation.

Students are based at the host institution to undertake their PhD research (i.e., either The University of Manchester, University of Glasgow or University of Oxford), which will be complemented by a comprehensive cohort-wide training and employability programme.

The RAINZ CDT programme follows a cohort-based training and research designed to ensure that graduates are not only subject matter experts, but also equipped with highly valuable skills in teamwork, sustainability, EDIA and wellbeing, industrial engagement, and commercialisation. Each cohort tackles an industry co-created, cross-sector challenge that requires a multi-disciplinary team of engineers and scientists to solve it. Researchers explore different aspects of the challenge, which are then integrated through the RAINZ CDT annual research sprints.

Find out more about the RAINZ CDT Training principles.

• Cohort research challenge: Long-term autonomous monitoring and maintenance of assets
• Year 1 MSc Course: MSc Advanced Control and Systems Engineering
• Year 2 – 4 PhD
  
  Location:
  
  The University of Manchester

Complex engineered systems are increasingly monitored by AI models which estimate health states, detect anomalies, and predict remaining useful life. These predictions are never certain: sensors degrade and drop out, operating conditions drift beyond training data, and degradation processes are inherently stochastic. Yet the decisions which rest on them - when to maintain, when to inspect, when to abort or extend a mission - are increasingly automated.

The central challenge is no longer producing predictions, but quantifying how much they can be trusted, understanding where that trust breaks down, and acting rationally when it does, whether the uncertainty resides in an autonomous platform, an embedded sensor in a remote structure, a degradation model, or the gap between a digital twin and the asset it represents.

Applicants should hold a First or strong Upper Second-class honours degree (2:1 with 65% average), or international equivalent, in Engineering, Computer Science, Physics, Mathematics, or a related discipline. Applicants should also demonstrate evidence of programming experience.

This project is open to Home students
.

Equality, diversity and inclusion are central to the RAINZ CDT. We welcome applications from individuals of all backgrounds and identities and are committed to a fair, inclusive recruitment process that minimises unconscious bias and supports individual needs.