Developing an AI/optimisation approach for the autonomous dismantling and packing of legacy nuclear installations

At some stage in the decommissioning of nuclear installations, it is inevitable that large metal structures (e.g., reactor vessels, gloveboxes, structural components) need to be cut into smaller pieces to be packed in containers, for temporary storage, permanent disposal or simply for transportation. Both cutting and packing cost money and usually, efficiency or cost-saving in one is achieved at the expense of the other (meaning a trade-off is always required). For example, consider a case where a radiation-protected human operator goes into a hot cell to take down an installation. Because of radiation exposure limits, there is usually not much time for deliberation. As such, the decision on how best to approach the problem is typically made there and then at the discretion of the human operator, and once a cut is made, there is no going back (i.e. there is very little margin for error). Due to scenarios like these, there is ongoing interest in the development of robotic/AI technologies for carrying out nuclear decommissioning tasks such as structure scanning, radiation mapping, and the dismantling and packaging of waste. The use of robotics/AI for such tasks can in principle remove constraints relating to radiation exposure time (hence allowing for longer operating times), whilst also allowing for more cost-efficient operation. This project is motivated by the need for more cost-effective ways to cut and package nuclear waste during decommissioning tasks. Currently, cutting and packing software can be used to perform cutting and packing trials entirely on a computer, but the problem with existing approaches is that they perform the cutting and packing tasks independently. This means that, for every set of objects generated by a cutting algorithm, a packing algorithm must then be used to trial different packing combinations for each set of objects. As such, if a human operator wishes to find the best way to cut an object so that the maximum amount of cut parts can be packed into a container, they will have to use a brute force approach to trial every possible cutting and packing combination until the best solution is found. This approach is problematic as even for a simple cutting/packing task the number of cutting/packing trials would quickly spiral out of control, resulting in excessively large computation time.



The aim of this project is to work out and introduce an artificial intelligence approach to link the two processes so that the following goals can be achieved:

Minimise total costs: the primary goal of this project is to create an algorithm which can minimise the total cost of the cutting/packing process.

Reduce number of cutting/packing trials: as stated, one of the problems with cutting/packing tasks is large the number of possible combinations. As such, a more intelligent approach is required to search for a more promising subset of combinations to trial rather than doing a brute force search over every possible combination.



Hypothesis:

Short of brute force trials, there is an intelligent and scientific way to optimise, under

various constraints, the cutting/packing process for overall cost saving, assuming accurate structural models and radiation maps are available (from in-situ, real-time, robotically operated scanning).



High Level Objectives:

Search and review relevant AI/optimization routes.

Develop them such that machine autonomous operation and decision-making is possible.

Demonstrate feasibility through simulations.

If possible, implement and demonstrate at lab scale using real robotics.

In GREEN we envisage there are potentially Impacts in several domains: the nuclear Sector; the wider Clean Growth Agenda; Government Policy & Strategy; and the Wider Public.

The two major outputs from Green will be Human Capital and Knowledge:

Human Capital: The GREEN CDT will deliver a pipeline of approximately 90 highly skilled entrants to the nuclear sector, with a broad understanding of wider sector challenges (formed through the training element of the programme) and deep subject matter expertise (developed through their research project). As evidenced by our letters of support, our CDT graduates are in high demand by the sector. Indeed, our technical and skills development programme has been co-created with key sector employers, to ensure that it delivers graduates who will meet their future requirements, with the creativity, ambition, and relational skills to think critically & independently and grow as subject matter experts. Our graduates are therefore a primary conduit to delivering impact via outcomes of research projects (generally co-created and co-produced with end users); as intelligent and effective agents of change, through employment in the sector; and strong professional networks.

Knowledge: The research outcomes from GREEN will be disseminated by students as open access peer reviewed publications in appropriate quality titles (with a target of 2 per student, 180 in total) and at respected conferences. Data & codes will be managed & archived for open access in accordance with institutional policies, consistent with UKRI guidelines. We will collaborate with our counterpart CDTs in fission and fusion to deliver a national student conference as a focus for dissemination of research, professional networking, and development of wider peer networks.

There are three major areas where GREEN will provide impact: the nuclear sector; clean growth; Policy and Strategy and Outreach.

the nuclear sector: One of our most significant impacts will be to create the next generation of nuclear research leaders. We will achieve this by carefully matching student experience with user needs.

clean growth - The proposed GREEN CDT, as a provider of highly skilled entrants to the profession, is therefore a critical enabler in supporting delivery of both the Clean Growth agenda, Nuclear Industry Strategy, and Nuclear Sector Deal, as evidenced by the employment rate of our graduates (85% into the sector industry) and the attached letters of support.

Policy and Strategy: The GREEN leadership and supervisory team provide input and expert advice across all UK Governments, and also to the key actors in the nuclear industry (see Track Records, Sections 3.3 & 5.1, CfS). Thus, we are well positioned to inculcate an understanding of the rapidly changing nuclear strategy and policy landscape which will shape their future careers.

Outreach to the wider public: Building on our track record of high quality, and acclaimed activities, delivered in NGN, GREEN will deliver an active programme of public engagement which we will coordinate with activities of other nuclear CDTs. Our training programme provides skills based training in public and media communication, enabling our students to act as effective and authoritative communicators and ambassadors. Examples of such activities delivered during NGN include: The Big Bang Fair, Birmingham 2014 - 2017; British Science Week, 2013 - 2017; ScienceX, Manchester; 2016 - 2018; and The Infinity Festival, Cumbria, 2017.