AI for Template based Multi-physics eMachine Design

Electrical machines are fundamental to the operation of modern society – from household devices and transportation to industrial operations and power generation. However, designing these devices is a slow and complex process. Many components of the process date back over a century and constrain the devices that can be produced. With technologies such as additive manufacturing removing many of the traditional constraints on design, it is important that the design process is also updated. Machine learning and artificial intelligence provide the potential for generating more efficient design tools capable of creating novel structures and reducing the overall cost of the process. The research in this project will result in a new generation of design tools capable of meeting the requirements of 21st century technology.

Faculty Supervisor:

David Lowther

Student:

Partner:

Siemens Electronic Design Automation ULC

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

McGill University

Program: