Assessment of Blast Induced Ground Vibrations by Artificial Neural Network
Abstract
Blast-induced ground motion is analyzed by means of two prediction methods. First conventional approach assumes several types of nonlinear dependence of peak particle velocity on scaled distance from the explosion charge, while the second technique implements a feed-forward three-layer back-propagation neural network with three nodes in input layer (total charge, maximum charge per delay and distance from explosive charge to monitoring point) and only one node in output layer (peak particle velocity). As a result, traditional predictors give acceptable prediction accuracy (r>0.7) when compared with registered values of peak particle velocity. Regarding the forecasting accuracy estimated by neural network, model with nine hidden nodes gives reasonable predictive precision (r>0.9), with much lower standard error in comparison to conventional predictors.
Keywords:
Artificial neural networks / prediction methods / vibrationsSource:
12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings, 2015, 55-60Publisher:
- Institute of Electrical and Electronics Engineers Inc.
Collections
Institution/Community
PharmacyTY - CONF AU - Kostić, Srđan AU - Vasović, Nebojša AU - Franović, Igor AU - Samčović, Andreja AU - Todorović, Kristina PY - 2015 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/2501 AB - Blast-induced ground motion is analyzed by means of two prediction methods. First conventional approach assumes several types of nonlinear dependence of peak particle velocity on scaled distance from the explosion charge, while the second technique implements a feed-forward three-layer back-propagation neural network with three nodes in input layer (total charge, maximum charge per delay and distance from explosive charge to monitoring point) and only one node in output layer (peak particle velocity). As a result, traditional predictors give acceptable prediction accuracy (r>0.7) when compared with registered values of peak particle velocity. Regarding the forecasting accuracy estimated by neural network, model with nine hidden nodes gives reasonable predictive precision (r>0.9), with much lower standard error in comparison to conventional predictors. PB - Institute of Electrical and Electronics Engineers Inc. C3 - 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings T1 - Assessment of Blast Induced Ground Vibrations by Artificial Neural Network SP - 55 EP - 60 DO - 10.1109/NEUREL.2014.7011458 ER -
@conference{ author = "Kostić, Srđan and Vasović, Nebojša and Franović, Igor and Samčović, Andreja and Todorović, Kristina", year = "2015", abstract = "Blast-induced ground motion is analyzed by means of two prediction methods. First conventional approach assumes several types of nonlinear dependence of peak particle velocity on scaled distance from the explosion charge, while the second technique implements a feed-forward three-layer back-propagation neural network with three nodes in input layer (total charge, maximum charge per delay and distance from explosive charge to monitoring point) and only one node in output layer (peak particle velocity). As a result, traditional predictors give acceptable prediction accuracy (r>0.7) when compared with registered values of peak particle velocity. Regarding the forecasting accuracy estimated by neural network, model with nine hidden nodes gives reasonable predictive precision (r>0.9), with much lower standard error in comparison to conventional predictors.", publisher = "Institute of Electrical and Electronics Engineers Inc.", journal = "12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings", title = "Assessment of Blast Induced Ground Vibrations by Artificial Neural Network", pages = "55-60", doi = "10.1109/NEUREL.2014.7011458" }
Kostić, S., Vasović, N., Franović, I., Samčović, A.,& Todorović, K.. (2015). Assessment of Blast Induced Ground Vibrations by Artificial Neural Network. in 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings Institute of Electrical and Electronics Engineers Inc.., 55-60. https://doi.org/10.1109/NEUREL.2014.7011458
Kostić S, Vasović N, Franović I, Samčović A, Todorović K. Assessment of Blast Induced Ground Vibrations by Artificial Neural Network. in 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings. 2015;:55-60. doi:10.1109/NEUREL.2014.7011458 .
Kostić, Srđan, Vasović, Nebojša, Franović, Igor, Samčović, Andreja, Todorović, Kristina, "Assessment of Blast Induced Ground Vibrations by Artificial Neural Network" in 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings (2015):55-60, https://doi.org/10.1109/NEUREL.2014.7011458 . .