New prediction models for mean particle size in rock blast fragmentation

Pinnaduwa Kulatilake, T. Hudaverdi, Qiong Wu

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The paper refers the reader to a blast data base developed in a previous study. The data base consists of blast design parameters, explosive parameters, modulus of elasticity and in situ block size. A hierarchical cluster analysis was used to separate the blast data into two different groups of similarity based on the intact rock stiffness. The group memberships were confirmed by the discriminant analysis. A part of this blast data was used to train a single-hidden layer back propagation neural network model to predict mean particle size resulting from blast fragmentation for each of the obtained similarity groups. The mean particle size was considered to be a function of seven independent parameters. An extensive analysis was performed to estimate the optimum value for the number of units for the hidden layer for each of the obtained similarity groups. The blast data that were not used for training were used to validate the trained neural network models. For the same two similarity groups, multivariate regression models were also developed to predict mean particle size. Capability of the developed neural network models as well as multivariate regression models was determined by comparing predictions with measured mean particle size values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the trained neural network models as well as multivariate regression models was found to be strong and better than the existing most applied fragmentation prediction model. Diversity of the blasts data used is one of the most important aspects of the developed models.

Original languageEnglish (US)
Pages (from-to)665-684
Number of pages20
JournalGeotechnical and Geological Engineering
Volume30
Issue number3
DOIs
StatePublished - Jun 2012

Fingerprint

particle size
fragmentation
rocks
Particle size
Rocks
prediction
rock
neural networks
Neural networks
back propagation
Cluster analysis
Blasting
Discriminant analysis
discriminant analysis
Backpropagation
blasting
modulus of elasticity
elasticity
train
cluster analysis

Keywords

  • Blast fragmentation
  • Cluster analysis
  • Discriminant analysis
  • Multivariate regression analysis
  • Neural networks
  • Rock mass

ASJC Scopus subject areas

  • Architecture
  • Geology
  • Soil Science
  • Geotechnical Engineering and Engineering Geology

Cite this

New prediction models for mean particle size in rock blast fragmentation. / Kulatilake, Pinnaduwa; Hudaverdi, T.; Wu, Qiong.

In: Geotechnical and Geological Engineering, Vol. 30, No. 3, 06.2012, p. 665-684.

Research output: Contribution to journalArticle

@article{37983b43b152436f859cdc5370c38085,
title = "New prediction models for mean particle size in rock blast fragmentation",
abstract = "The paper refers the reader to a blast data base developed in a previous study. The data base consists of blast design parameters, explosive parameters, modulus of elasticity and in situ block size. A hierarchical cluster analysis was used to separate the blast data into two different groups of similarity based on the intact rock stiffness. The group memberships were confirmed by the discriminant analysis. A part of this blast data was used to train a single-hidden layer back propagation neural network model to predict mean particle size resulting from blast fragmentation for each of the obtained similarity groups. The mean particle size was considered to be a function of seven independent parameters. An extensive analysis was performed to estimate the optimum value for the number of units for the hidden layer for each of the obtained similarity groups. The blast data that were not used for training were used to validate the trained neural network models. For the same two similarity groups, multivariate regression models were also developed to predict mean particle size. Capability of the developed neural network models as well as multivariate regression models was determined by comparing predictions with measured mean particle size values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the trained neural network models as well as multivariate regression models was found to be strong and better than the existing most applied fragmentation prediction model. Diversity of the blasts data used is one of the most important aspects of the developed models.",
keywords = "Blast fragmentation, Cluster analysis, Discriminant analysis, Multivariate regression analysis, Neural networks, Rock mass",
author = "Pinnaduwa Kulatilake and T. Hudaverdi and Qiong Wu",
year = "2012",
month = "6",
doi = "10.1007/s10706-012-9496-3",
language = "English (US)",
volume = "30",
pages = "665--684",
journal = "International Journal of Mining Engineering",
issn = "0263-4546",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - New prediction models for mean particle size in rock blast fragmentation

AU - Kulatilake, Pinnaduwa

AU - Hudaverdi, T.

AU - Wu, Qiong

PY - 2012/6

Y1 - 2012/6

N2 - The paper refers the reader to a blast data base developed in a previous study. The data base consists of blast design parameters, explosive parameters, modulus of elasticity and in situ block size. A hierarchical cluster analysis was used to separate the blast data into two different groups of similarity based on the intact rock stiffness. The group memberships were confirmed by the discriminant analysis. A part of this blast data was used to train a single-hidden layer back propagation neural network model to predict mean particle size resulting from blast fragmentation for each of the obtained similarity groups. The mean particle size was considered to be a function of seven independent parameters. An extensive analysis was performed to estimate the optimum value for the number of units for the hidden layer for each of the obtained similarity groups. The blast data that were not used for training were used to validate the trained neural network models. For the same two similarity groups, multivariate regression models were also developed to predict mean particle size. Capability of the developed neural network models as well as multivariate regression models was determined by comparing predictions with measured mean particle size values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the trained neural network models as well as multivariate regression models was found to be strong and better than the existing most applied fragmentation prediction model. Diversity of the blasts data used is one of the most important aspects of the developed models.

AB - The paper refers the reader to a blast data base developed in a previous study. The data base consists of blast design parameters, explosive parameters, modulus of elasticity and in situ block size. A hierarchical cluster analysis was used to separate the blast data into two different groups of similarity based on the intact rock stiffness. The group memberships were confirmed by the discriminant analysis. A part of this blast data was used to train a single-hidden layer back propagation neural network model to predict mean particle size resulting from blast fragmentation for each of the obtained similarity groups. The mean particle size was considered to be a function of seven independent parameters. An extensive analysis was performed to estimate the optimum value for the number of units for the hidden layer for each of the obtained similarity groups. The blast data that were not used for training were used to validate the trained neural network models. For the same two similarity groups, multivariate regression models were also developed to predict mean particle size. Capability of the developed neural network models as well as multivariate regression models was determined by comparing predictions with measured mean particle size values and predictions based on one of the most applied fragmentation prediction models appearing in the blasting literature. Prediction capability of the trained neural network models as well as multivariate regression models was found to be strong and better than the existing most applied fragmentation prediction model. Diversity of the blasts data used is one of the most important aspects of the developed models.

KW - Blast fragmentation

KW - Cluster analysis

KW - Discriminant analysis

KW - Multivariate regression analysis

KW - Neural networks

KW - Rock mass

UR - http://www.scopus.com/inward/record.url?scp=84861810998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861810998&partnerID=8YFLogxK

U2 - 10.1007/s10706-012-9496-3

DO - 10.1007/s10706-012-9496-3

M3 - Article

AN - SCOPUS:84861810998

VL - 30

SP - 665

EP - 684

JO - International Journal of Mining Engineering

JF - International Journal of Mining Engineering

SN - 0263-4546

IS - 3

ER -