Artificial Neural Net for He nano-bubble identification in structural materials for nuclear power applications

Nuclear power plants provide stable, carbon-free electricity to Canadians. In order to ensure their safe operations, materials in the reactors must be characterized on a regular basis. This project aims at developing an Artificial Intelligence—an artificial neural network—with the aim of automating the indentification of helium bubbles in Ni-based alloys currently in use in Canadian Nuclear power plants. These bubbles have a diameter of the order of nanometers, and can be observed using transmission electron microscopes. Currently, the analysis of the micrographs is done manually. The Artificial Intelligence would help automate this tedious process.

Faculty Supervisor:

Laurent Béland

Student:

Christopher Anderson

Partner:

Canadian Nuclear Laboratories

Discipline:

Engineering - mechanical

Sector:

Energy

University:

Queen's University