A Case Study of Prediction and Analysis of Unplanned Dilution in an Underground Stoping Mine using Artificial Neural Network
Исследование прогнозирования и анализа непреднамеренного разубоживания на подземной шахте с камерной системой разработки с использованием искусственной нейронной сети
2014-08-31
SCID: 54.1/7qau2nc5
Discuss with AI
artificial neural network (ANN)blast hole lengthconnection weight algorithm (CWA)underground stoping miningunplanned dilution
Figures from the paper
Abstract (AI)
스토핑 채광법은 현재 가장 보편적으로 이용되고 있는 지하 금속광 채광법 중 하나이다. 그러나 채광과정에서 발생하는 확정선외 혼입은 광산 전반의 생산성을 떨어뜨리며 때때로 폐광의 주요 원인을 제공하기도 하여 그 예측과 관리가 시급한 실정이다. 이를 위해 본 연구는 서 호주의 한 지하광산에서 조사한 자료를 바탕으로 인공 신경망(ANN)을 이용하여 보다 신뢰성 있는 확정선외 혼입 예측모델을 제시하였다. 또한, 연결가중 알고리즘(CWA)에 의한 요인분석을 통해 확정선외 혼입의 영향인자에 대한 기여도 분석을 실시하였다. 제안된 확정선 외 혼입 예측 ANN 모델의 학습과 시험 단계의 상관계수는 0.9641과 0.7933으로 강한 상관관계를 보였으며, CWA분석결과 발파공 길이(BHL)과 절리 방향 안전계수(SFJ)의 기여도가 18.78%와 17.99%로 다른 인자에 비해 비교적 중요한 영향인자 임을 확인할 수 있었다. Stoping method has been acknowledged as one of the typical metalliferous underground mining methods. Notwithstanding with the popularity of the method, the majority of stoping mines are suffering from excessive unplanned dilution which often becomes as the main cause of mine closure. Thus a reliable unplanned dilution management system is imperatively needed. In this study, reliable unplanned dilution prediction system is introduced by adopting artificial neural network (ANN) based on data investigated from one underground stoping mine in Western Australia. In addition, contributions of input parameters were analysed by connection weight algorithm (CWA). To validate the reliability of the proposed ANN, correlation coefficient (R) was calculated in the training and test stage which shown relatively high correlation of 0.9641 in training and 0.7933 in test stage. As results of CWA application, BHL (Length of blast hole) and SFJ (Safety factor of Joint orientation) show comparatively high contribution of 18.78% and 19.77% which imply that these are somewhat critical influential parameter of unplanned dilution.
Key Findings
1
An artificial neural network was developed to predict unplanned dilution using data from an underground stoping mine in Western Australia.
2
Connection weight analysis identified blast-hole length as a major contributor to unplanned dilution, with an 18.78% contribution.
3
Joint-orientation safety factor was also identified as a critical influential parameter, with a reported contribution of 19.77%.
4
The ANN achieved correlation coefficients of 0.9641 during training and 0.7933 during testing, indicating strong predictive performance.
5
The proposed ANN and parameter-contribution analysis provide a basis for more reliable unplanned dilution management in stoping mines.
Research Object
Unplanned dilution in an underground stoping mine in Western Australia
Research Subject
Prediction and influential-factor contributions of unplanned dilution, particularly the effects of blast-hole length and joint-orientation safety factor
Publication Details
Publication Date
2014-08-31
Journal
Publisher
ISSN
Cited by
1
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest