A. Srivastava; B. Singh Choudhary; M. Sharma
Abstract
Blast-induced ground vibration (PPV) evaluation for a safe blasting is a long-established criterion used mainly by the empirical equations. However, the empirical equations are again considering a limited information. Therefore, using Machine Learning (ML) tools [Support Vector Machine (SVM) and Random ...
Read More
Blast-induced ground vibration (PPV) evaluation for a safe blasting is a long-established criterion used mainly by the empirical equations. However, the empirical equations are again considering a limited information. Therefore, using Machine Learning (ML) tools [Support Vector Machine (SVM) and Random Forest (RF)] can help in this context, and the same is applied in this work. A total of 73 blasts are monitored and recorded in this work. For the ML tools, the dataset is divided into the 80-20 ratio for the training and testing purposes in order to evaluate the performance capacity of the models. The prediction accuracies by the SVM and RF models in predicting the PPV values are satisfactory (up to 9% accuracy). The results obtained show that the coefficient of determination (R2) for RF and SVM is 0.81 and 0.75, respectively. Compared to the existing linear regressions, this work recommends using a machine learning regression model for the PPV prediction.
D. Mohammadi; R. Mikaeil; J. Abdollahei Sharif
Abstract
The blasting method is one of the most important operations in most open-pit mines that has a priority over the other mechanical excavation methods due to its cost-effectiveness and flexibility in operation. However, the blasting operation, especially in surface mines, imposes some environmental problems ...
Read More
The blasting method is one of the most important operations in most open-pit mines that has a priority over the other mechanical excavation methods due to its cost-effectiveness and flexibility in operation. However, the blasting operation, especially in surface mines, imposes some environmental problems including the ground vibration as one of the most important ones. In this work, an evaluation system is provided to study and select the best blasting pattern in order to reduce the ground vibration as one of the hazards in using the blasting method. In this work, 45 blasting patterns used for the Sungun copper mine are studied and evaluated to help determine the most suitable and optimum blasting pattern for reducing the ground vibration. Additionally, due to the lack of certainty in the nature of ground and the analyses relating to this drilling system, in the first step, a combination of the imperialist competitive algorithm and k-means algorithm is used for clustering the measured data. In the second step, one of the multi-criteria decision-making methods, namely TOPSIS (Technique for Order Performance by Similarity to Ideal Solution), is used for the final ranking. Finally, after evaluating and ranking the studied patterns, the blasting pattern No. 27 is selected. This pattern is used with the properties including a hole diameter of 16.5 cm, number of holes of 13, spacing of 4 m, burden of 3 m, and ammonium nitrate fuel oil of 1100 Kg as the most appropriate blasting pattern leading to the minimum ground vibration and reduction of damages to the environment and structures constructed around the mine.