Title
Evaluation and prediction of flyrock resulting from blasting operations using empirical and computational methods.
Abstract
Mines, quarries and construction sites face environmental impacts, such as flyrock, due to blasting operations. Flyrock may cause damage to structures and injury to human. Therefore, flyrock prediction is required to determine safe blasting zone. In this regard, 232 blasting operations were investigated in five granite quarries, Malaysia. Blasting parameters comprising maximum charge per delay and powder factor were prepared to predict flyrock using empirical and intelligent methods. An empirical graph was proposed to predict flyrock distance for different powder factor values. In addition, using the same datasets, two intelligent systems, namely artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were used to predict flyrock. Considering some model performance indices including coefficient of determination (R 2), value account for and root mean squared error and also using simple ranking procedure, the best flyrock prediction models were selected. It was found that the ANFIS model can predict flyrock with higher performance capacity compared to ANN predictive model. R 2 values of testing datasets are 0.925 and 0.964 for ANN and ANFIS techniques, respectively, suggesting the superiority of the ANFIS technique in predicting flyrock.
Year
DOI
Venue
2016
10.1007/s00366-015-0402-5
Engineering With Computers
Keywords
Field
DocType
Blasting, Flyrock, Empirical graph, Artificial neural network, Adaptive neuro-fuzzy inference system
Data mining,Ranking,Intelligent decision support system,Mean squared error,Rock blasting,Artificial intelligence,Adaptive neuro fuzzy inference system,Coefficient of determination,Predictive modelling,Artificial neural network,Mathematics,Machine learning
Journal
Volume
Issue
ISSN
32
1
1435-5663
Citations 
PageRank 
References 
18
1.05
12
Authors
6