광업 분야의 딥러닝 기술 적용연구 사례분석
Case Analysis of Applications for Deep Learning Technology in the Mining Industry
2
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
본 논문에서는 딥러닝 기술을 국내 광업분야에 효과적으로 도입하기 위하여 광업 분야의 딥러닝 기술 적용연구들을 조사하고 정리하였다. 딥러닝은 ANN에 기원을 둔 머신러닝 알고리즘으로, 지질학적 문제와 같은 고차원비선형 문제의 추상화에 특화되어 있다. 딥러닝 기술이 조사, 탐사, 개발, 광산운영, 재해분석에 이르는 광업주기에 따라 어떻게 적용되었는지 조사되었다. 조사 및 탐사단계에서는 지구화학탐사, 물리탐사, 지질도, 단층선, 지형정보를융합하여 광물 부존가능성 지도화를 수행하는 연구가 다수 제안되었다. 광산 개발 및 관리 단계에서는 센서나 카메라에 의해 측정된 광산 현황 자료로 광산 내 상황 자동감지, 솔루션 자동연산, 자동 장비제어에 대한 연구가 수행되고 있었다. 재해 분석 단계는 상황인식 및 재해 예측이 주된 목적이었다. 딥러닝 기술이 국내광업분야에 효과적으로 도입되기 위해서 관련된 국내 적용연구가 요구된다.
Abstract
Applications for deep learning technology in the mining industry were investigated to utilize deep learning technology in the domestic mining field. Deep learning is specialized in abstracting high-dimensional nonlinear problems, such as geological problems. The author investigated the applications of deep learning technology for mining cycle that is divided into investigation, exploration, development, mine operation, and disaster analysis. In the survey and exploration phase, a number of studies have been proposed to carry out mineral potential mapping by integrating geochemical and geophysical explorations, geological maps, fault lines, and topographic information. In the mine development and management phase, studies on autonomous situation detection, automatic calculation, and equipment control were carried out using mine status data measured by sensors or cameras. The hazard analysis phase was mainly used for status awareness and hazard prediction. In order for deep learning technology to be effectively utilized in the domestic mining field, relevant domestic research is required.
참고문헌 (36)
- Ballard, D. H., "Modular learning in neural networks", Proc. AAAI, pp.279~284 (1987)
- Bengio, Y., "Representation learning: A review and new perspectives", IEEE Trans. PAMI, special issue Learning Deep Architectures (2013)
- Bewley, A., "Background appearance modeling with applications to visual object detectin in an open-pit mine", J. of Field Robot, 34(1), pp.53~73 (2016)
- Bishop, C. M., "Pattern Recognition and Machine Learning" (2007), Springer
- Boulle, M., "Predicting dangerous seismic events in coal mines under distribution drift", Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS), pp.221~224 (2018)
- 최용근, "광산에서 ICT의 역할과 기술 동향", 한국자원공학회지, 54(1), pp.66~78 (2017), 한국자원공학회
- Du, S., "A new machine-learing prediction model for slope deformation of an open-pit mine : an evaluation of field data", Energies, 12, pp.1288~1302 (2019)
- Ford, A., "Evaluating geological complexity and complexity gradients as controls on copper mineralization, Mt Isa Inlier", Austral. J. of Earth Sci, 55, pp.13~23 (2008)
- Geng, Y., "Seismic events prediction using deep temporal convolution networks", J. of Elec. and Comp. Eng, 2019, pp.14~ (2019)
- Hongquan Guo, "Deep neural network and whale optimization algorithm to assess flyrock induced by blasting", Engineering with Computers (2019), Springer Science and Business Media LLC[DOI]
- Hinton. G. E., "Learning multiple layers of representation", Trends in Cognitive Sciences, 11, pp.428~434 (2007)
- Hochreiter, S., "Long short-term memory", Neur. Comp, 9(8), pp.1735~1780 (1997)
- Anuj Karpatne, "Machine Learning for the Geosciences: Challenges and Opportunities", IEEE Transactions on Knowledge and Data Engineering, 31(8), pp.1544~1554 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- LeCun, Y., "Backpropagation applied to handwritten zip code recognition", Neur. Comp, 1, pp.541~551 (1989)
- LeCun, Y., "Deep learning", Nature, 521, pp.436~ (2015)
- 이채영, "머신러닝 기술의 광업 분야 도입을 위한 활용사례 분석", 터널과 지하공간, 29(1), pp.1~11 (2019), 한국암반공학회[DOI]
- Shi Li, "Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data", Neural Computing and Applications (2019), Springer Science and Business Media LLC[DOI]
- Lim, H. J., "Development direction of fraud detection ststem technology", J. of the Korea Ins. of Comm. Sci, 34(3), pp.37~46 (2017)
- Xiangang Luo, "Mine landslide susceptibility assessment using IVM, ANN and SVM models considering the contribution of affecting factors", PLOS ONE, 14(4), pp.e0215134~ (2019), Public Library of Science (PLoS)[DOI]
- Marek, S., "Application of rule induction al-gorithms for analysis of data collected by seismic hazard monitoring systems in coal mines", Archives of Ming Sciences, 55, pp.91~114 (2010)
- Mnih, V., "Playing Atari with Deep Reinforcement Learning", ~ (2013)
- Hoang Nguyen, "A comparative study of artificial neural networks in predicting blast-induced air-blast overpressure at Deo Nai open-pit coal mine, Vietnam", Neural Computing and Applications (2018), Springer Science and Business Media LLC[DOI]
- "What's the Difference Between AI, Machine Learning, and Deep Learning?" (2018)[URL]
- Tessema, A., "Mineral systems analysis and artificial neural network modeling of chromite prospectivity in the western limb of the bushveld complex", South Africa, Nat. Resour. Resch, 26(4), pp.465~488 (2017)
- Vincent, P., "Stacked denoising autoencoders : learning useful representations in a deep network with a local denoising criterion", J. of Mach. Learn. Resch, 11, pp.3371~3408 (2010)
- Williams, R. J., "Learning representations by back-propagating errors", Nature, 323(6088), pp.533~536 (1986)
- Xiong, W., "Seismic fault detection with convolution neural network", Geophysics, 83(5), pp.O97~O103 (2018)
- Xiong, Y., "Recognition of geochemical anomalies using a deep autoencoder network", Comp &Geosci, 86, pp.75~82 (2016)
- Xiong, Y., "Mapping mineral prospectivity through big data analytics and a deep learning algorithm", Ore Geology Reviews, 102, pp.811~817 (2018)
- Yinka-Banjo, C., "Autonomous multi-robot behaviours for safety inspection under the constraints of underground mine Terrains", Ubiq. Comp. and Comm. J, 7(5), pp.1316~1328 (2012)
- Zhang, C., "Methane gas density monitoring and predicting based on RFID sensor tag and CNN algorithm", Electronics, 7(5), pp.69~81 (2018)
- Zhang, S., "Integration of auto-encoder network with densitybased spatial clustering for geochemical anomaly detection for mineral exploration", Comp & Geosci, 130, pp.43~56 (2019)
- Zuo, R., "Deep learning and its application in geochemical mapping", Earth-Science Reviews, 192, pp.1~14 (2019)