Mining Smarter: Hydrocarbon Usage Optimization

At present, the data collected from the Fuel Management System (FMS) is only being used to a fraction of its potential. Our proposed solution is to delve into FMS data along with maintenance and operations information on critical mine site equipment such as heavy haul trucks, excavation equipment, and their light vehicle fleet to optimize the use of fuels and lubricants. This information coupled with GPS data from fleet vehicles would allow us to ensure every drop of these valuable and environmentally damaging resources are used only when needed and to their full potential. Additionally, this data will allow for extremely accurate calculation of GHG emissions from vehicle fleets and the impacts of fuel quality, driver habits, terrain, and preventative maintenance cycles on overall hydrocarbon emissions.
We will use machine learning and artificial intelligence to analyze FMS data and integrate it with other data sources on mine sites. A software solution will be offered to minesites which prioritizes opportunities to be actioned with key performance indicators monitored to ensure a reduction in consumption of hydrocarbons.

Faculty Supervisor:

Irene Cheng

Student:

Partner:

Innoflo

Discipline:

Computer science

Sector:

Mining

University:

University of Alberta

Program: