Predicting and controlling the ground vibration using gene expression programming (GEP) and teaching–learning-based optimization (TLBO) algorithms

Ground vibration is one of the most significant issues resulting from the blasting operation. This paper presents two empirical relationships based on gene expression programming (GEP) and teaching–learning-based optimization (TLBO) algorithms for predicting blast-induced peak particle velocity (PPV...

Full description

Saved in:
Bibliographic Details
Published in:Environmental earth sciences Vol. 80; no. 22; p. 740
Main Authors: Dehghani, Hesam, Jodeiri Shokri, Behshad, Mohammadzadeh, Hoshiar, Shamsi, Reza, Abbas Salimi, Nasrin
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2021
Springer Nature B.V
Subjects:
Algorithms
Biogeosciences
Blasting
Comparative analysis
Correlation coefficient
Correlation coefficients
Curve fitting
Earth and Environmental Science
Earth Sciences
Empirical analysis
Environmental Science and Engineering
Gene expression
Geochemistry
Geology
Ground motion
Hydrology/Water Resources
Iran
Machine learning
Optimization
Orbital velocity
Original Article
Parameters
Predictive control
Root-mean-square errors
Statistical methods
Statistics
Terrestrial Pollution
Vibration
villages
Iran
Peak particle velocity (PPV)
Gene expression programming (GEP)
Teaching–learning-based optimization (TLBO)
Blasting
ISSN:1866-6280, 1866-6299
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Ground vibration is one of the most significant issues resulting from the blasting operation. This paper presents two empirical relationships based on gene expression programming (GEP) and teaching–learning-based optimization (TLBO) algorithms for predicting blast-induced peak particle velocity (PPV) at Galali Iron Mine, western Iran. For this purpose, data on 13 parameters were collected from 34 blasting blocks in the studied mine before having the data processed using statistical methods. Eventually, four parameters, including burden, mean hole depth, charge per delay ratio, and distance to monitoring station, were identified as the most effective factors. PPV was also considered as the output parameter of the model. Then, exploring the best curve-fitting relationships between input and output data, an empirical relationship was developed by applying the GEP algorithm. Afterward, the TLBO algorithm was utilized to optimize the developed relationship. A comparative analysis based on statistical parameters such as correlation coefficient (R 2 ), root mean square error (RMSE), and mean absolute percentage error (MAPE) indicated the superior accuracy of TLBO algorithm compared to the GEP method. Finally, a blasting pattern was formulated to attenuate the PPV at the center of the Galali Village from 10 mm/s to 1 mm/s while increasing the mine production from 5500 tons to 17,500 tons per blasting block.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1866-6280
1866-6299
DOI:10.1007/s12665-021-10052-7