Scholarly record
USING DECISION TREES TO BUILD A FAILURE CRITERION FOR AN UNDERGROUND MINE
Abstract
One of the major concerns in all underground mine excavations is the stability of the stopes, the empty spaces which are created throughout the excavation process. Typically, the mining engineer supports or reinforces the stopes when needed, by means of rockbolts, wire meshes and steel sets. At the same time, a monitoring system based on geotechnical or geodetic measurements can provide against tiny displacements of control targets. This paper presents the application of artificial intelligence techniques, namely, decision trees, to turn underground mine data into knowledge. Particularly, geodetic measurements, engineering and geologic observations that originate from the Red Rock underground mine in central Greece, are analyzed by an open source decision tree algorithm. The algorithm builds a failure criterion for the mine, which is dynamically adapted to posterior cases.
Publication details
References1
Quinlan J.R. C4.5: Programs for machine learning, Morgan Kaufmann, San Francisco, 1993
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.