Dilution prediction and reduction in underground mines based on stoping methods using artificial intelligence

Given that dilution is a problem that reduces the profit of many underground operations, the dilution monitoring, prediction, and reduction convey the capability to increase operational efficiency. The proposed research aims to develop an unplanned dilution monitoring, prediction, and reduction tool. The research methodology will be based on artificial intelligence (AI)-based models. More specifically, the research will focus on the applicability of ensemble classifiers, naive Bayes classifiers, logistic regression, and neural networks. Using data gathered from the underground mining stopes (e.g., drilling and blasting design and configuration; stope geometry; the dip and strike of stopes; in-situ stresses; mining depth and methods; grade variability; and rock type and characteristics), AI models will be built.

Faculty Supervisor:

Mustafa Kumral

Student:

Partner:

DT Solutions Services

Discipline:

Engineering

Sector:

Information and cultural industries

University:

McGill University

Program: