Method of Predicting Ore Dilution Based on a Neural Network and Its Application
Метод прогнозирования разубоживания руды на основе нейронной сети и его применение
2020-02-19
SCID: 54.1/w95n3y9s
Discuss with AI
back-propagation neural networkequivalent linear overbreak sloughhydraulic radiusmodified stability numberore dilution prediction
Figures from the paper
Abstract (AI)
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 r2 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.
Key Findings
1
A three-layer back-propagation neural network with six hidden neurons predicts unplanned ore dilution using four geotechnical and blasting variables.
2
Applied to a test stope at the Sandaoqiao lead–zinc mine, the method calculated unplanned ore dilution as 0.717 m versus the measured 0.70 m.
3
The application produced a 2.4% relative error, outperforming the empirical graph method’s 0.8 m estimate and numerical simulation’s 0.55 m estimate.
4
The model was trained and tested on 120 datasets, achieving an average R² of 0.9761, mean squared error of 0.0001, and approximately 6.2% relative prediction error.
5
The study confirms that the neural-network approach can predict unplanned ore dilution in practical mining applications.
Research Object
Unplanned ore dilution in underground stopes, particularly at the Sandaoqiao lead–zinc mine
Research Subject
Prediction accuracy of ELOS-quantified unplanned ore dilution and its influencing input-variable relationships
Publication Details
Publication Date
2020-02-19
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest