Multiscale, Multi-fidelity and Multiphysics Bayesian Neural Network (BNN) Machine Learning (ML) Surrogate Models for Modelling Design Based Accidents

Find Similar History 12 Claim Ownership Request Data Change Add Favourite

Title
Multiscale, Multi-fidelity and Multiphysics Bayesian Neural Network (BNN) Machine Learning (ML) Surrogate Models for Modelling Design Based Accidents

CoPED ID
de073067-1f28-46f7-a873-fe1b3c52f65d

Status
Active


Value
No funds listed.

Start Date
Sept. 30, 2022

End Date
Sept. 30, 2026

Description

More Like This


A floating nuclear power plant (NPP) is a site with one or more nuclear reactors located on a platform at sea. It is an autonomous site that can provide electrical power and process heat to countries with a small land mass, but which are geographical close to the sea. These types of NPPs can also provide fresh clean drinking water to dry areas via desalination techniques. They can be built using modern modular construction techniques at a factory or shipyard, eliminating the need to set up a nuclear licensed site for its construction and operation. The location of these types of NPPs is also greatly simplified since it is not necessary to conduct viability studies on the land and land environment. However, the sea or coastal environment does make it necessary to take several factors into account. These factors include the access for operational staff and equipment as well as the need to ensure that any radioactive material cannot leak into the sea. Given the widespread development, and deployment, of large scale, medium scale and small modular PWRs, the aim of this PhD proposal is to focus on the analysis of these types of NPPs within this PhD proposal. This enables Singapore to gain experience in understanding the operational and safety aspects of PWRs; and floating NPPs barges and platforms. In addition, this proposal will enable Singapore to develop key skills and technology for modelling and simulating (M&S) the operational behaviour of PWRs as well as design basis accidents (DBA) in PWRs. It will also build upon the current PhD studentship that is funded by National University of Singapore (NUS) Nuclear Research and Safety Initiative (SNRSI) which is focussed on developed a Bayesian neural network (BNN) based surrogate modelling and simulation (M&S) framework for investigating thermal fatigue issues associated with load following floating NPPs.


More Information

Potential Impact:
It cannot be overstated how important reducing CO2 emissions are in both electricity production for homes and industry but also in reducing road pollution by replacing petrol/diesel cars with electric cars in the next 20 years. These ambitions will require a large growth in electricity production from low carbon sources that are both reliable and secure and must include nuclear power in this energy mix. Such a future will empower the vision of a prosperous, secure nation with clean energy. To do this the UK needs more than 100 PhD level people per year to enter the nuclear industry. This CDT will impact this vision by producing 70, or more, both highly and broadly trained scientists and engineers, in nuclear power technologies, capable of leading the UK new build and decommissioning programmes for future decades. These students will have experience of international nuclear facilities e.g. ANSTO, ICN Pitesti, Oak Ridge, Mol, as well as a UK wide perspective that covers aspects of nuclear from its history, economics, policy, safety and regulation together with the technical understanding of reactor physics, thermal hydraulics, materials, fuel cycle, waste and decommissioning and new reactor designs. These individuals will have the skill set to lead the industry forward and make the UK competitive in a global new build market worth an estimated £1.2tn. Equally important is reducing the costs of future UK projects e.g. Wylfa, Sizewell C by 30%, to allow the industry and new build programme to grow, which will be worth £75bn domestically and employ tens of thousands per project.

We will deliver a series of bespoke training courses, including on-line e-learning courses, in Nuclear Fuel Cycle, Waste and Decommissioning; Policy and Regulation; Nuclear Safety Management; Materials for Reactor Systems, Innovation in Nuclear Technology; Reactor Operation and Design and Responsible Research. These courses can be used more widely than just the CDT educating students in other CDTs with a need for nuclear skills, other university courses related to nuclear energy and possibly for industry as continual professional development courses and will impact the proposed Level 8 Apprenticeship schemes the nuclear industry are pursuing to fill the high level skills gap.

The CDT will deliver world-class research in a broad field of nuclear disciplines and disseminate this work through outreach to the public and media, international conferences, published journal articles and conference proceedings. It will produce patents where appropriate and deliver impact through start-up companies, aided by Imperial Innovations, who have a track record of turning research ideas into real solutions. By working and listening to industry, and through the close relationships supervisory staff have with industrial counterparts, we can deliver projects that directly impact on the business of the sponsors and their research strategies. There is already a track record of this in the current CDT in both fission and fusion fields. For example there is a student (Richard Pearson) helping Tokamak Energy engage with new technologies as part of his PhD in the ICO CDT and as a result Tokamak Energy are offering the new CDT up to 5 studentships.

Another impact we expect is an increasing number of female students in the CDT who will impact the industry as future leaders to help the nuclear sector reach its target of 40% by 2030.
The last major impact of the CDT will be in its broadening scope from the previous CDT. The nuclear industry needs to embrace innovation in areas such as big data analytics and robotics to help it meet its cost reduction targets and the CDT will help the industry engage with these areas e.g. through the Bristol robotics hub or Big Data Institute at Imperial.

All this will be delivered at a remarkable value to both government and the industry with direct funding from industry matching the levels of investment from EPSRC.

Michael Bluck SUPER_PER

Subjects by relevance
  1. Nuclear power plants
  2. Nuclear energy
  3. Safety and security
  4. Nuclear safety
  5. Industry
  6. Nuclear waste

Extracted key phrases
  1. Multiphysics Bayesian Neural Network
  2. Multiscale
  3. Nuclear industry
  4. Nuclear power technology
  5. Nuclear power plant
  6. Nuclear reactor
  7. Nuclear skill
  8. International nuclear facility
  9. Nuclear energy
  10. Nuclear discipline
  11. UK new build
  12. Machine Learning
  13. New CDT
  14. Global new build market worth
  15. Fidelity

Related Pages

UKRI project entry

UK Project Locations