Estimation of ambiguous blast-induced ground vibration using intelligent models: A case study. (April 2018)

• Record Type: Journal Article
• Authors: Prashanth, Ragam; Nimaje, DS
• Is Part Of: Noise & vibration worldwide. Volume 49:Number 4(2018)
• Page Start: 147
• Page End: 157
• Publication Date: 2018-04
• Subjects: Peak particle velocity -- blast-induced ground vibration -- support vector machine -- back propagation neural network -- radial basis function neural network -- cascaded feedforward network -- coefficient of determination; Noise control -- Periodicals; Damping (Mechanics) -- Periodicals; Soundproofing -- Periodicals; Damping (Mechanics); Noise control; Soundproofing; Periodicals; 620.205
• DOI: 10.1177/0957456518781858
• Languages: English
• ISSNs: 0957-4565

Abstract

Blasting is an economical and viable operation for reliable excavation of hard rock in mining and civil construction. An ambiguous ground vibration generated by blasting is unenviable and causes grievous damage to nearby inhabitants, residential premises, and other sensitive sites. Accordingly, the proper assessment of indistinct blast-induced ground vibration is a requisite to pinpoint the safe limits in and around mines. An endeavor has been made in this article to apply four predictive models, namely, support vector machine, feed forward back propagation neural network, cascaded forward back propagation neural network, and radial basis function neural network to estimate the ground vibration caused by blasting operation conducted at Mine-A, India. In this article, a total number of 121 blasting operations with relevant parameters are recorded. The most influential parameters of ground vibration are the number of holes, burden, spacing, hole diameter, hole depth, top stemming, maximum explosive charge per delay, and the distance from blast source, which were considered as input parameters. Ground vibration is measured in terms of peak particle velocity and is considered as output. The performance indicators of constructed network models were chosen as the coefficient of determination (R 2 ), root mean square error, and variance account for. Among all constructed intelligent models, the radial basis function neural network with architecture 8-80-1 and R 2 of 0.9918, root mean square error of 4.4076, and variance account for of 99.1800 was found to be optimum. Sensitivity analysis showed that the number of holes, burden, and top stemming are the most effective parameters leads to ground vibration due to blasting.