광업 데이터의 시계열 분석을 통해 실리카 농도를 예측하기 위한 머신러닝 모델
A Machine Learning Model for Predicting Silica Concentrations through Time Series Analysis of Mining Data
0
조회
0
다운로드
9
인용
0
참고문헌
키워드
초록
Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.
Abstract
Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.
참고문헌 (22)
- Why 70, "30 or 80", 20 Relation Between Training and Testing Sets: A Pedagogical Explanation, pp.2018, ~[DOI]
- Breiman, L, "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
- Chen, T., "Xgboost : A scalable tree boosting system", Proceedings of the 22nd acm SigkddInternational Conference on Knowledge Discovery and Data mining, pp.785~794 (2016)
- 최성현, "최적화 하이퍼 파라미터의 학습자 기반 배깅 모델을 활용한 태양광 출력 예측", 전기학회논문지, 69(7), pp.978~984 (2020), 대한전기학회
- Effect of Bubble Size, Gas Holdup and Superficial Gas Velocity on Metallurgical Performance in an Industrial Flotation Cell, "Gorain, B. K.", JKMRC, ~ (1995)
- Heimes, F. O., "Recurrent neural networks for remaining useful life estimation", 2008 international conference on prognostics and health management, pp.1~6 (2008), IEEE
- 허남규, "다변량 시계열 모형을 이용한 항공 수요 예측 연구", 응용통계연구, 22(5), pp.1007~1017 (2009), 한국통계학회
- 장동률, "랜덤 포레스트를 활용한 작품 가격 예측 모형 연구", 신뢰성 응용연구, 20(1), pp.34~42 (2020), 한국신뢰성학회[DOI]
- 장형두, "4차 산업혁명에 대처하는 호주 광업의 변화와 미래 전망", 한국자원공학회지, 56(5), pp.490~513 (2019), 한국자원공학회
- 정해성, "빅데이터에서의 상관성 측도", 신뢰성 응용연구, 18(3), pp.208~212 (2018), 한국신뢰성학회[DOI]
- 김정균, "랜덤 포레스트를 이용한 심전도 기반 생체 인증", 전자공학회논문지, 54(6), pp.100~105 (2017), 대한전자공학회
- Kohavi, "A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection", International Joint Conference on Artificial Intelligence, 14(12), pp.1137~1143 (1995)
- Kwame O. E., "Machine Learning-based Quality Prediction in the Froth Flotation Process of Mining", Master, pp.2019
- 이채영, "머신러닝 기술의 광업 분야 도입을 위한 활용사례 분석", 터널과 지하공간, 29(1), pp.1~11 (2019), 한국암반공학회[DOI]
- Lee, Y. H., "Big data Cloud Service for Manufacturing Process Analysis", The Korean Journal of BigData, 1(1), pp.41~51 (2016)
- Molinaro., "Prediction Error Estimation: A Comparison of Resampling Methods", Bioinformatics, 21(15), pp.3301~3307 (2005), Oxford University Press
- 박근태, "MODWT의 시계열 데이터 적용과 ARIMA와 DBNs 결합모델을 이용한 예측", 대한산업공학회지, 43(6), pp.474~481 (2017), 대한산업공학회[DOI]
- Sawyerr, C. T., "Prediction of bubble size distribution in mechanical flotation cells", Journal of the Southern African Institute of Mining and Metallurgy, 98(4), pp.179~185 (1998)
- Seo, M. Y., "A Study on the Seasonal Adjustment of Time Series and Demand Forecasting for Electronic Product Sales", Journal of Applied Reliability, 3(1), pp.13~39 (2003)
- 탁정호, "빅데이터를 활용한 레이더 시스템의 SRU 단위 고장률 예측방안", 신뢰성 응용연구, 18(4), pp.339~348 (2018), 한국신뢰성학회[DOI]
- 윤동희, "딥러닝을 이용한 시계열데이터 군집화", 신뢰성 응용연구, 19(2), pp.167~178 (2019), 한국신뢰성학회[DOI]
- 윤혜선, "지역빈도해석 및 다중회귀분석을 이용한 산악형 강수해석", 한국수자원학회 논문집, 42(6), pp.465~480 (2009), 한국수자원학회