Paper Details

[ Downloads: 0 | Abstract Viewed: 170 | Pages: 11 ]

Abstract of the Article

Note: English CIVILICA is in its Trial Period so Full Texts can not be provided! Persian users can download it here

Prediction of Open Pit Mine Blasting Powder Factor Based Upon Neural Networks

Author:
[ J. Ghazanfary ] - Department of mining, Azad University, Science & Research Branch, Iran

Abstract:

In the last decades, several researches have worked to develop equations to calculate the powder factor for open pit mine blasting operations. Most of these equations must be adjusted by trial and error method based on field data. In this research based upon a series of observations and required input parameters, the Neural Networks (NN) algorithm is used to develop a model for powder factor prediction .The input parameters which are used including (1) rock mass description (2) joint plane orientation (3) joint plan spacing (4) specific gravity index (5) hardness and the output is powder factor. The data is collected from Chador-Maloo Iron mine of Iran and multilayer feed forward NN using a back propagation learning algorithm and Sigmoid function are used as an activating function. Using field data from Chador-Maloo mine, applying NN, the model is developed with one input layer, two hidden layers and one output layer to predict the powder factor. The average actual powder factor is 0.23kg/t in ore and 0.2kg/t in waste materials and the predicted one in ore and waste are on 0.2349kg/t and 0.2007kg/t respectively, which shows a good agreement between the actual amount and the predicted one.

Keywords:

Prediction powder factor, Neural Networks (NN)