Date Available

12-3-2021

Year of Publication

2021

Document Type

Master's Thesis

Degree Name

Master of Science in Mining Engineering (MSMIE)

College

Engineering

Department/School/Program

Mining Engineering

Advisor

Dr. Joseph Sottile

Abstract

In recent years, a great deal of work has been conducted in automating mining equipment with the goals of increasing worker health and safety and increasing mine productivity. Automating vehicles such as load-haul-dumps been successful even in underground environments where the use of global positioning systems are unavailable. This thesis addresses automating the operation of a shuttle car, specifically focusing on positioning the shuttle car under the continuous miner coal-discharge conveyor during cutting and loading operations. This task requires recognition of the target and precise control of the tramming operation because a specific orientation and distance from the coal discharge conveyor is needed to avoid coal spillage. The proposed approach uses a stereo depth camera mounted on a small-scale mockup of a shuttle car. Machine learning algorithms are applied to the camera output to identify the continuous miner coal-discharge conveyor and segment the scene into various regions such as roof, ribs, and personnel. This information is used to plan the shuttle car path to the continuous miner coal-discharge conveyor. These methods are currently applied on 1/6th scale continuous miner and shuttle car in an appropriately scaled mock mine.

Digital Object Identifier (DOI)

https://doi.org/10.13023/etd.2021.466

Funding Information

The research reported was supported by the National Institute for Occupational Safety and Health (NIOSH) under Contract Number 75D30120C08908. The content is solely the responsibility of the authors and does not necessarily represent the official views of NIOSH.

Download

Share

COinS