Method of Predicting Ore Dilution Based on a Neural Network and Its Application

Abstract

A back-propagation neural network prediction model with three layers and six neurons in the hidden layer is established to overcome the limitation of the equivalent linear overbreak slough (ELOS) empirical graph method in estimating unplanned ore dilution. The modified stability number, hydraulic radius, average deviation of the borehole, and powder factor are taken as input variables and the ELOS of quantified unplanned ore dilution as the output variable. The training and testing of the model are performed using 120 sets of data. The average fitting degree r 2 of the prediction model is 0.9761, the average mean square error is 0.0001, and the relative error of the prediction is approximately 6.2%. A method of calculating the unplanned ore dilution is proposed and applied to a test stope of the Sandaoqiao lead-zinc mine. The calculated unplanned ore dilution is 0.717 m, and the relative error (i.e., the difference between calculation and measurement of 0.70 m) is 2.4%, which is better than the relative errors for the empirical graph method and numerical simulation (giving dilution values of 0.8 and 0.55 m, respectively). The back-propagation neural network prediction model is confirmed to predict the unplanned ore dilution in real applications.

Moving towards deep underground mineral resources: Drivers, challenges and potential solutions

“…Scientists routinely discover new insights from legacy data that ranges from characterisation, prediction and hypothesis testing of deep geological structures to geometallurgical properties of various ores (e.g., Cowan, 2020;Mutshafa et al, 2022). From an engineering perspective, legacy data has been successfully used to create machine learning algorithms that are highly specific to currently relevant data (e.g., Wu and Zhou, 1993;Jafrasteh et al, 2018;Zhao and Niu, 2020). Therefore, legacy data lowers the cost of technological adoption.…”

Stope Structural Parameters Design towards Green and Deep Mining: A Review

“…A geometrically large stope can lead to the failure and/or collapse of surrounding rocks, impeding normal and safe operations. In the meantime, the collapse mixes waste rocks with ores, increasing the cost of ore upgrading and increasing unplanned dilution, thereby increasing the cost of beneficiation [45,46]. On the contrary, geometrically conservative stope parameters can lead to large mining and cutting quantities and a low ratio of ore recovery, increasing production costs and reducing economic benefits.…”

Design Method and Application of Stope Structure Parameters in Deep Metal Mines Based on an Improved Stability Graph

“…From the actual production conditions of mines at home and abroad, on the one hand, the stope structure parameters play a decisive role in the stability of the stope, and on the other hand, they also affect the economic benefits of mining [11,12], as shown in Figure 1.…”

“…From the actual production conditions of mines at home and abroad, on the one hand, the stope structure parameters play a decisive role in the stability of the stope, and on the other hand, they also affect the economic benefits of mining [11,12], as shown in Figure 1. When the structural parameters of the stope are too large, it leads to instability and caving of ore and rock, increases the loss and dilution, and makes it impossible to operate normally and safely.…”