ABSTRACT
Many underground metal mining operations use diesel-powered equipment which emits diesel particulate matter (DPM) into the atmosphere posing a health and safety hazard to expose mine workers. The United States Environmental Protection Agency (EPA) and National Institute for Occupational Safety and Health (NIOSH) have classified DPM as a possible carcinogen creating greater need to control exposure to DPM in the workplace. Within current underground metal mine planning practices, ventilation requirements are often considered after the production schedule has been developed, leading to operational challenges in managing DPM levels. We present a method of estimating DPM using artificial neural network (ANN) for use in underground production scheduling. By incorporating DPM production from various underground mining activities, the resulting production schedules can help better utilize ventilation and production resources in addition to allowing operations to measure the impacts of various non-ventilation DPM reduction methods, e.g., biofuels, electric equipment. The results here show that there is significant potential in predicting DPM concentrations for underground production activities. This research aims to improve the mine environment by providing a tool to estimate DPM that can be incorporated into the production schedule, thereby influencing strategic and tactical-level planning decisions.
