Doctoral Dissertations

Keywords and Phrases

Convolutional neural network; Discrete element method; Dragline excavation; Earthmoving; Object detection; Terrain recognition


"The contribution of coal to global energy is expected to remain above 30% through 2030. Draglines are the preferred excavation equipment in most surface coal mines. Recently, studies toward dragline excavation efficiency have focused on two specific areas. The first area is dragline bucket studies, where the goal is to develop new designs which perform better than conventional buckets. Drawbacks in the current approach include operator inconsistencies and the inability to physically test every proposed design. Previous simulation models used Distinct Element Methods (DEM) but they over-predict excavation forces by 300% to 500%. In this study, a DEM-based simulation model has been developed to predict bucket payloads within a 16.55% error. The excavation model includes a novel method for calibrating formation parameters. The method combines DEM-based tri-axial material testing with the XGBoost machine learning algorithm to achieve prediction accuracies of between 80.6% and 95.54%.

The second area is dragline vision studies towards efficient dragline operation. Current dragline vision models use image segmentation methods that are neither scalable nor multi-purpose. In this study, a scalable and multi-purpose vision model has been developed for draglines using Convolutional Neural Networks. This vision system achieves an 87.32% detection rate, 80.9% precision and 91.3% recall performance across multiple operation tasks. The main novelty of this research includes the bucket payload prediction accuracy, formation parameter calibration and the vision system accuracy, precision and recall performance toward improving dragline operating efficiencies"--Abstract, page iii.


Frimpong, Samuel

Committee Member(s)

Maerz, Norbert H.
Awuah-Offei, Kwame, 1975-
Galecki, Greg
Aouad, Nassib


Mining Engineering

Degree Name

Ph. D. in Mining Engineering


Itasca Consulting Group


Missouri University of Science and Technology

Publication Date

Fall 2018


xv, 205 pages

Note about bibliography

Includes bibliographic references (pages 194-204).


© 2018 Godfred Somua-Gyimah, All rights reserved.

Document Type

Dissertation - Open Access

File Type




Thesis Number

T 11443

Electronic OCLC #