Prediction of blast induced vibrations in the structures of Karoun III power plant and dam

The damage of unallowable blast induced vibrations on the newly constructed concrete structures in the excavations of the Karoun III project results in a decrease in the safety of its structures. Therefore prediction and control of the vibrations are of importance in the study area. To predict the vibrations in this area, two main approaches were used and the results were interpreted and compared. The vibrations were first predicted using several widely used empirical models. Then, an artificial neural network (ANN) was used. In the ANN model, maximum charge per delay, total charge per round, distance from blast site, direction of firing, blast hole length, number of blast holes, total delay in milliseconds, number of delay intervals and average specific charge were taken into consideration as input parameters. However, the ANN approach showed very high correlation and very small estimation error, the best empirical model resulted in a reliable correlation and an acceptable error of estimation. By considering all aspects the empirical approach was used in practice. Finally a plot based on standard values of vibrations was proposed for the safety of the structures.