A scalable solution for sensing and sorting ore in the mineral mining process

This project intends to research the building of scalable, low-cost and robust alternatives and improvements to existing systems for mineral sensing and sorting in order to achieve greater productivity and efficiency by means of improving speed and accuracy in the process of mining minerals from low grade rocks. The project will combine developments in embedded and streaming systems, parallel computing and machine-learning to create a more specialized system for this domain. The project will be based on an existing platform of MineSense, a leading company in this area. This research will provide MineSense with insights into alternative hardware and software systems, as well as useful research data with regards to trade-offs in light of scalability, latency and accuracy, which should prove beneficial for design and planning for their current and future mining systems.

Faculty Supervisor:

Dr. Alan Wagner

Student:

Sarwar Alam

Partner:

MineSense Technologies

Discipline:

Computer science

Sector:

Mining and quarrying

University:

University of British Columbia