Feasibility of ICA in approximating ground vibration resulting from mine blasting

Precise prediction of blast-induced ground vibration is an essential task to reduce the environmental effects in the surface mines, civil and tunneling works. This research investigates the potential of imperialist competitive algorithm (ICA) in approximating ground vibration as a result of blasting...

Full description

Saved in:
Bibliographic Details
Main Authors: Armaghani, Danial Jahed, Hasanipanah, Mahdi, Amnieh, Hassan Bakhshandeh, Mohamad, Edy Tonnizam
Format: Article
Published: Springer-Verlag London Ltd 2016
Subjects:
Online Access:http://eprints.utm.my/id/eprint/72811/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84984780895&doi=10.1007%2fs00521-016-2577-0&partnerID=40&md5=a9b8d23ac28c5327a5e1eb57122f3231
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknologi Malaysia
Description
Summary:Precise prediction of blast-induced ground vibration is an essential task to reduce the environmental effects in the surface mines, civil and tunneling works. This research investigates the potential of imperialist competitive algorithm (ICA) in approximating ground vibration as a result of blasting at three quarry sites, namely Ulu Tiram, Pengerang and Masai in Malaysia. In ICA modeling, two forms of equations, namely power and quadratic, were developed. For comparison aims, several empirical models were also used. In order to develop the ICA and empirical models, maximum charge weight used per delay (W) and the distance between blasting sites and monitoring stations (D) were utilized as the independent variables, while, peak particle velocity (PPV), as a blast-induced ground vibration descriptor, was utilized as the dependent variable. Totally, 73 blasting events were monitored, and the values of W, D and PPV were carefully measured. Two statistical functions, i.e., root mean square error and coefficient of multiple determination (R2) were used to compare the performance capability of those prediction models. Simulation results show that the proposed ICA quadratic form can get more accurate predicting results than the ICA power form and empirical models.