Simulation of blasting induced ground vibration by using artificial neural network

• Main Authors: Mohamad, Edy Tonnizam, Noorani, Seyed Ahmad, Armaghani, Danial Jahed, Saad, Rosli
• Format: Article
• Published: EJGE 2012
• Subjects: TA Engineering (General). Civil engineering (General)
• Online Access: http://eprints.utm.my/id/eprint/33508/; http://www.ejge.com/2012/Ppr12.218alr.pdf
• Institution: Universiti Teknologi Malaysia

Blast-induced ground vibration is one of the most important environmental impacts of blasting operations because it may cause severe damage to structures and plants in nearby environment. Estimation of ground vibration levels induced by blasting has vital importance for restricting the environmental effects of blasting operations. This study is aimed to compare the ground vibrations predicted from empirical formula and analytical program with the real data. Several predictor equations have been proposed by various researchers to predict ground vibration prior to blasting, but these are site specific and not generally applicable beyond the specific conditions. To evaluate and calculate the blast-induced ground vibration by incorporating blast design and rock strength, artificial neural networks (ANN) was used. In this study, 12 experiments based on blasting parameters, for modeling in MATLAB software and neural network systems were evaluated to predict the Peak Particle Velocity (PPV) and frequency. It was found that in this study, USBM is one of the most accurate empirical formula for the prediction. The advantage of the ANN compared to other empirical relations used for prediction of PPV is the fact that there was no limitation in the number of input parameters. The correlation coefficients for overall analysis for velocity and frequency are 0.997 and 0.989 respectively. The average relative error obtained from ANN estimation was 0.01 % for velocity and 3.96 % for frequency which are negligible when compared with the those predicted by empirical relationships. This study found that ANN method produced more accurate prediction than the empirical formula.