Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Neural network approach to model the flow of crude ore
2004 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

In order to decrease ore dilution and ore losses it is necessary to control the draw of the mucking material during the loading operation. In LKAB, the mucked rock inside the LHD’s scoop is weighed before dumping into the ore passes. This creates a series of data indicating the variation of the rock material during the mining cycle for each drilling ring, which constitutes a database for draw control purposes. This thesis is divided into two parts. The first part is about the estimation of the ore content in the mucked material in the bucket of the LHD machine. Different ways to estimate draw control parameters are investigated. The second part treats the prediction of the weight of the LHD bucket based on the sequence of loaded scoops obtained from the same drilling ring using neural networks. Through the application of neural networks one does not intend to study the physical phenomenon which requires the modelling of determinant variables. Instead this approach is used to predict the mining output, i.e., the rock material mucked out from the drilling rings. Results from the application of neural networks show that this is a good approach. Neural networks are promising for implementation of expert systems for remote loading operation in LKAB. Several suggestions for improvements or even implementations in the mine are given.

Place, publisher, year, edition, pages
2004.
Keyword [en]
Technology, loading operation, neural networks, control and prediction, automation parameter estimates
Keyword [sv]
Teknik
Identifiers
URN: urn:nbn:se:ltu:diva-56885ISRN: LTU-EX--04/125--SELocal ID: da024989-5eaa-4d6c-8ffa-37e3925d570bOAI: oai:DiVA.org:ltu-56885DiVA, id: diva2:1030272
Subject / course
Student thesis, at least 30 credits
Educational program
Applied Geoscience and Mining, master's level
Examiners
Note
Validerat; 20101217 (root)Available from: 2016-10-04 Created: 2016-10-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 11 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf