A neural network approach to predict mean particle size in rock blast fragmentation

Q. Wu, Pinnaduwa Kulatilake, T. Hudaverdi, C. Kuzu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Neural network methodology is used to predict mean particle size resulting from rock blast fragmentation. A blast data base developed in a previous study is used in the current study. A part of this blast data was used to train a single-hidden layer back propagation neural network model for each of the similarity groups obtained in the same previous study. Levenberg-Marquardt algorithm provided the most stable and efficient training out of the four algorithms evaluated. An extensive analysis was performed using a part of the blast data to estimate the optimum number of units for the hidden layer for each similarity group. The remaining blast data are used to validate the trained neural network models. Capability of the developed neural network models is determined by comparing predictions with measured values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the neural network models was found to be strong and better than the existing most applied model. Diversity of the blasts data used is one of the most important aspects of the developed models. The developed neural network models are suitable for practical use at mines.

Original languageEnglish (US)
Title of host publicationSME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011
Pages245-254
Number of pages10
StatePublished - 2011
EventSME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011 - Denver, CO, United States
Duration: Feb 28 2011Mar 2 2011

Other

OtherSME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011
CountryUnited States
CityDenver, CO
Period2/28/113/2/11

Fingerprint

fragmentation
Particle size
Rocks
particle size
Neural networks
rock
prediction
back propagation
Blasting
Backpropagation
blasting
train
methodology

Keywords

  • Blasting
  • Fragmentation
  • Neural networks
  • Rock mass

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology

Cite this

Wu, Q., Kulatilake, P., Hudaverdi, T., & Kuzu, C. (2011). A neural network approach to predict mean particle size in rock blast fragmentation. In SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011 (pp. 245-254)

A neural network approach to predict mean particle size in rock blast fragmentation. / Wu, Q.; Kulatilake, Pinnaduwa; Hudaverdi, T.; Kuzu, C.

SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011. 2011. p. 245-254.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, Q, Kulatilake, P, Hudaverdi, T & Kuzu, C 2011, A neural network approach to predict mean particle size in rock blast fragmentation. in SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011. pp. 245-254, SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011, Denver, CO, United States, 2/28/11.
Wu Q, Kulatilake P, Hudaverdi T, Kuzu C. A neural network approach to predict mean particle size in rock blast fragmentation. In SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011. 2011. p. 245-254
Wu, Q. ; Kulatilake, Pinnaduwa ; Hudaverdi, T. ; Kuzu, C. / A neural network approach to predict mean particle size in rock blast fragmentation. SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011. 2011. pp. 245-254
@inproceedings{b211da20b8104811a81deb86d4b076e9,
title = "A neural network approach to predict mean particle size in rock blast fragmentation",
abstract = "Neural network methodology is used to predict mean particle size resulting from rock blast fragmentation. A blast data base developed in a previous study is used in the current study. A part of this blast data was used to train a single-hidden layer back propagation neural network model for each of the similarity groups obtained in the same previous study. Levenberg-Marquardt algorithm provided the most stable and efficient training out of the four algorithms evaluated. An extensive analysis was performed using a part of the blast data to estimate the optimum number of units for the hidden layer for each similarity group. The remaining blast data are used to validate the trained neural network models. Capability of the developed neural network models is determined by comparing predictions with measured values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the neural network models was found to be strong and better than the existing most applied model. Diversity of the blasts data used is one of the most important aspects of the developed models. The developed neural network models are suitable for practical use at mines.",
keywords = "Blasting, Fragmentation, Neural networks, Rock mass",
author = "Q. Wu and Pinnaduwa Kulatilake and T. Hudaverdi and C. Kuzu",
year = "2011",
language = "English (US)",
isbn = "9781617829727",
pages = "245--254",
booktitle = "SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011",

}

TY - GEN

T1 - A neural network approach to predict mean particle size in rock blast fragmentation

AU - Wu, Q.

AU - Kulatilake, Pinnaduwa

AU - Hudaverdi, T.

AU - Kuzu, C.

PY - 2011

Y1 - 2011

N2 - Neural network methodology is used to predict mean particle size resulting from rock blast fragmentation. A blast data base developed in a previous study is used in the current study. A part of this blast data was used to train a single-hidden layer back propagation neural network model for each of the similarity groups obtained in the same previous study. Levenberg-Marquardt algorithm provided the most stable and efficient training out of the four algorithms evaluated. An extensive analysis was performed using a part of the blast data to estimate the optimum number of units for the hidden layer for each similarity group. The remaining blast data are used to validate the trained neural network models. Capability of the developed neural network models is determined by comparing predictions with measured values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the neural network models was found to be strong and better than the existing most applied model. Diversity of the blasts data used is one of the most important aspects of the developed models. The developed neural network models are suitable for practical use at mines.

AB - Neural network methodology is used to predict mean particle size resulting from rock blast fragmentation. A blast data base developed in a previous study is used in the current study. A part of this blast data was used to train a single-hidden layer back propagation neural network model for each of the similarity groups obtained in the same previous study. Levenberg-Marquardt algorithm provided the most stable and efficient training out of the four algorithms evaluated. An extensive analysis was performed using a part of the blast data to estimate the optimum number of units for the hidden layer for each similarity group. The remaining blast data are used to validate the trained neural network models. Capability of the developed neural network models is determined by comparing predictions with measured values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the neural network models was found to be strong and better than the existing most applied model. Diversity of the blasts data used is one of the most important aspects of the developed models. The developed neural network models are suitable for practical use at mines.

KW - Blasting

KW - Fragmentation

KW - Neural networks

KW - Rock mass

UR - http://www.scopus.com/inward/record.url?scp=80052473842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052473842&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80052473842

SN - 9781617829727

SP - 245

EP - 254

BT - SME Annual Meeting and Exhibit and CMA 113th National Western Mining Conference 2011

ER -