Developing a least squares support vector machine for estimating the blast-induced flyrock

In blasting operations, the main purpose is to provide appropriate rock fragmentation and to avoid adverse effects such as flyrock and vibration. This paper presents the applicability of least squares support vector machines (LS-SVM) for estimating the blast-induced flyrock. For comparison aim, supp...

Full description

Saved in:
Bibliographic Details
Published in:Engineering with computers 2018-10, Vol.34 (4), p.709-717
Main Authors: Rad, Hima Nikafshan, Hasanipanah, Mahdi, Rezaei, Mohammad, Eghlim, Amin Lotfi
Format: Article
Language:English
Subjects:
Blasting
CAE) and Design
Calculus of Variations and Optimal Control
Optimization
Case studies
Charge density
Classical Mechanics
Computer Science
Computer-Aided Engineering (CAD
Control
Datasets
Estimation
Least squares method
Math. Applications in Chemistry
Mathematical and Computational Engineering
Mathematical models
Original Article
Regression analysis
Sensitivity analysis
Statistical analysis
Support vector machines
Systems Theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In blasting operations, the main purpose is to provide appropriate rock fragmentation and to avoid adverse effects such as flyrock and vibration. This paper presents the applicability of least squares support vector machines (LS-SVM) for estimating the blast-induced flyrock. For comparison aim, support vector regression (SVR) was also employed. The case study was carried out in the Gole-E-Gohar iron mine of Iran in which the values of burden to spacing ratio, hole length to burden ratio, subdrilling, stemming, charge per delay, rock density and powder factor were measured for 90 blasting operations. The mentioned seven parameters were used as the independent or input parameters in modeling, while, the values of flyrock distance were assigned as the models output. To train the models, 72 datasets were adopted and then the remaining 18 datasets were adopted to test the models. The models performance was compared by several statistical criteria such as R square ( R 2 ) and mean square error (MSE). According to obtained results, the LS-SVM with the R 2 of 0.969 and MSE of 16.25 can prove more useful than the SVR with the R 2 of 0.945 and MSE of 31.58 in estimation of blast-induced flyrock. At the end, sensitivity analysis was also performed and according to the results, powder factor and rock density were the most effective parameters on the flyrock in this case study.
ISSN:0177-0667
1435-5663
DOI:10.1007/s00366-017-0568-0