Application of PCA and Bayesian MCMC to discriminate between water sources in seabed gold mines

YAN Bing-qian; REN Fen-hua; CAI Mei-feng; GUO Qi-feng; WANG Pei-tao

doi:10.13374/j.issn2095-9389.2019.06.03.004

Volume 41 Issue 11

Dec. 2019

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Engineering > 2019 > 41(11): 1412-1421

YAN Bing-qian, REN Fen-hua, CAI Mei-feng, GUO Qi-feng, WANG Pei-tao. Application of PCA and Bayesian MCMC to discriminate between water sources in seabed gold mines[J]. Chinese Journal of Engineering, 2019, 41(11): 1412-1421. doi: 10.13374/j.issn2095-9389.2019.06.03.004

Citation:

YAN Bing-qian, REN Fen-hua, CAI Mei-feng, GUO Qi-feng, WANG Pei-tao. Application of PCA and Bayesian MCMC to discriminate between water sources in seabed gold mines[J]. Chinese Journal of Engineering, 2019, 41(11): 1412-1421. doi: 10.13374/j.issn2095-9389.2019.06.03.004

Citation:

PDF( 920 KB)

Application of PCA and Bayesian MCMC to discriminate between water sources in seabed gold mines

doi: 10.13374/j.issn2095-9389.2019.06.03.004

YAN Bing-qian^{1, 2},
REN Fen-hua^{1, 2
,
,},
CAI Mei-feng^{1, 2},
GUO Qi-feng^{1, 2},
WANG Pei-tao^{1, 2}

1.
School of Civil and Resource Engineering, University of Science and Technology Beijing, Beijing 100083, China
2.
Beijing Key Laboratory of Urban Underground Space Engineering, University of Science and Technology Beijing, Beijing 100083, China

More Information

Corresponding author: E-mail: renfh_2001@163.com
Received Date: 2019-06-03
Publish Date: 2019-11-01

Abstract

Abstract

Water hazards in submarine gold mines pose a great threat to mine production, construction personnel, and mining equipment, and represent one of the natural disasters that occur in mining. To prevent and control accidents, it is critical to quickly and effectively identify water sources. Cracks in the rocks surrounding the roadway in the Sanshandao Gold Mine are a widespread and long-term water gushing phenomenon. The main sources of mine water hazards in mining areas are seawater, Quaternary water, bedrock fissure water, and groundwater. To accurately and quickly identify mine water sources and effectively prevent inrushes of mine water and water-hazard threats, the hydrogeological conditions and chemical composition of water samples from different monitoring points were analyzed and six indicators, i.e., Mg²⁺, Na⁺+K⁺, Ca²⁺, SO₄ ^2?, Cl^?, and HCO₃ ^?, were selected as discriminant factors. Based on the analysis principle of the Bayesian algorithm, the Markov chain Monte Carlo (MCMC) approach was introduced into the Bayesian method. A Bayesian discriminant analysis model was then constructed using SPSS Statistics and the MCMC Bayesian method. The posterior distribution estimated by the algorithm is based on water-sample information, which enables the analysis of the mine water source. Based on the water-sample data from a water intake point at the Sanshandao Gold Mine, detailed analysis and verification were performed, and a water-source model for the inrush of mine water was established. An analysis of different water samples was then performed. Through the selection of variables, variables with a strong discriminant ability and high degree of correlation were introduced into the discriminant function to obtain the Bayesian statistical function, thus enabling a discriminatory analysis of the water sources. The accuracy and practicability of the proposed Bayesian mine-water-source identification model were verified. This model has certain significance for guiding future field work and water-hazard prevention and control efforts.
- mine water source,
- Bayes method,
- Markov Chain Monte Carlo (MCMC),
- principal component analysis (PCA),
- water sample analysis,
- mine water inrush

FullText(HTML)

References(28)

References

[1]	李克蓬, 馬鳳山, 張洪訓, 等. 海底金礦礦坑涌水水源判識及演化研究. 工程地質學報, 2017, 25(1):180 Li K P, Ma Fe S, Zhang H X, et al. Recharge source identification and evolution of inflowing water in a seabed gold mine. J Eng Geol, 2017, 25(1): 180
[2]	李長洪, 卜磊, 魏曉明, 等. 深部開采安全機理及災害防控現狀與態勢分析. 工程科學學報, 2017, 39(8):1129 Li C H, Bu L, Wei X M, et al. Current status and future trends of deep mining safety mechanism and disaster prevention and control. Chin J Eng, 2017, 39(8): 1129
[3]	柴金飛, 金愛兵, 高永濤, 等. 基于矩張量反演的礦山突水孕育過程. 工程科學學報, 2015, 37(3):267 Chai J F, Jin A B, Gao Y T, et al. Water inrush inoculation process in mines based on moment tensor inversion. Chin J Eng, 2015, 37(3): 267
[4]	Li L P, Lei T, Li S C, et al. Risk assessment of water inrush in karst tunnels and software development. Arabian J Geosci, 2015, 8(4): 1843 doi: 10.1007/s12517-014-1365-3
[5]	徐星, 田坤云, 鄭吉玉. 基于遺傳BP神經網絡模型的礦井突水水源判別. 工業安全與環保, 2017, 43(11):21 doi: 10.3969/j.issn.1001-425X.2017.11.006 Xu X, Tian K Y, Zheng J Y. Discrimination of mine water inrush source based on genetic BP neural network model. Ind Saf Environ Prot, 2017, 43(11): 21 doi: 10.3969/j.issn.1001-425X.2017.11.006
[6]	陳紅江, 李夕兵, 劉愛華. 礦井突水水源判別的多組逐步Bayes判別方法研究. 巖土力學, 2009, 30(12):3655 doi: 10.3969/j.issn.1000-7598.2009.12.016 Chen H J, Li X B, Liu A H. Studies of water source determination method of mine water inrush based on Bayes’ multi-group stepwise discriminant analysis theory. Rock Soil Mech, 2009, 30(12): 3655 doi: 10.3969/j.issn.1000-7598.2009.12.016
[7]	陳紅江, 李夕兵, 劉愛華, 等. 煤層底板突水量的距離判別分析預測方法. 煤炭學報, 2009, 34(4):487 doi: 10.3321/j.issn:0253-9993.2009.04.011 Chen H J, Li X B, Liu A H, et al. Forecast method of water inrush quantity from coal floor based on distance discriminant analysis theory. J China Coal Soc, 2009, 34(4): 487 doi: 10.3321/j.issn:0253-9993.2009.04.011
[8]	Liu Z X, Dang W G, He X Q. Undersea safety mining of the large gold deposit in Xinli District of Sanshandao Gold Mine. Int J Miner Metall Mater, 2012, 19(7): 574 doi: 10.1007/s12613-012-0598-y
[9]	Li X, Wang B, Liu Y, et al. Stochastic feature mapping for pac-bayes classification. Mach Learning, 2015, 101(1-3): 5 doi: 10.1007/s10994-015-5525-9
[10]	Yan H X, Moradkhani H. Toward more robust extreme flood prediction by Bayesian hierarchical and multimodeling. Nat Hazards, 2016, 81(1): 203 doi: 10.1007/s11069-015-2070-6
[11]	Zhou F, Bai X R. High-resolution sparse subband imaging based on Bayesian learning with hierarchical priors. IEEE Trans Geosci Remote Sensing, 2018, 56(8): 4568 doi: 10.1109/TGRS.2018.2827072
[12]	Ruijters E, Stoelinga M. Fault tree analysis: A survey of the state-of-the-art in modeling, analysis and tools. Comput Sci Rev, 2015(15-16): 29
[13]	Fisher R A. Inverse probability and the use of likelihood. Mathematical Proceed Cambridge Philosophical Soc, 1932, 28(3): 257 doi: 10.1017/S0305004100010094
[14]	Duan G L, Hu W X, Wang J R. Research on the natural image super-resolution reconstruction algorithm based on compressive perception theory and deep learning model. Neurocomputing, 2016, 208: 117 doi: 10.1016/j.neucom.2015.12.125
[15]	Unesi M, Noaparast M, Shafaei S Z, et al. Modeling the effects of ore properties on water recovery in the thickening process. Int J Miner Metall Mater, 2014, 21(9): 851 doi: 10.1007/s12613-014-0981-y
[16]	黃玉雄, 李更豐, 別朝紅, 等. 分布式綜合能源系統可靠性評估. 智慧電力, 2017, 45(7):43 doi: 10.3969/j.issn.1673-7598.2017.07.008 Huang Y X, Li G F, Bie Z H, et al. Reliability evaluation of distributed integrated energy system. Smart Power, 2017, 45(7): 43 doi: 10.3969/j.issn.1673-7598.2017.07.008
[17]	Caroleo B, Palumbo E, Osella M, et al. A knowledge-based multi-criteria decision support system encompassing cascading effects for disaster management. Int J Inf Technol Decis Mak, 2018, 17(5): 1469 doi: 10.1142/S021962201850030X
[18]	趙培, 熊亮. 氯氣管道泄漏源項識別反演問題. 科技導報, 2013, 31(26):48 doi: 10.3981/j.issn.1000-7857.2013.26.007 Zhao P, Xiong L. Inverse problem for the identification of the source term in chlorine pipeline leak. Sci Technol Rev, 2013, 31(26): 48 doi: 10.3981/j.issn.1000-7857.2013.26.007
[19]	陳海洋, 滕彥國, 王金生, 等. 基于Bayesian-MCMC方法的水體污染識別反問題. 湖南大學學報(自然科學版), 2012, 39(6):74 Chen H Y, Teng Y G, Wang J S, et al. Event source identification of water pollution based on Bayesian-MCMC. J Hunan Univ Nat Sci, 2012, 39(6): 74
[20]	Yan X S, Sun J, Hu C Y. Research on contaminant sources identification of uncertainty water demand using genetic algorithm. Cluster Computing, 2017, 20(2): 1007 doi: 10.1007/s10586-017-0787-6
[21]	Kruschke J K, Liddell T M. The Bayesian New Statistics: Hypothesis testing, estimation, meta-analysis, and power analysis from a Bayesian perspective. Psychonomic Bull Rev, 2018, 25(1): 178 doi: 10.3758/s13423-016-1221-4
[22]	魯帆, 嚴登華. 基于廣義極值分布和Metropolis-Hastings抽樣算法的貝葉斯MCMC洪水頻率分析方法. 水利學報, 2013, 44(8):942 Lu F, Yan D H. Bayesian MCMC flood frequency analysis method based on generalized extreme value distribution and Metropolis-Hastings sampling algorithm. J Hydraul Eng, 2013, 44(8): 942
[23]	楊曉彤, 王來斌, 張忠文. Fisher方法在礦井突水水源判別中的應用. 科技信息, 2014(11):97 doi: 10.3969/j.issn.1001-9960.2014.11.070 Yang X T, Wang L B, Zhang Z W. The application of fisher approach to discrimination of mine water-inrush source. Sci Technol Inf, 2014(11): 97 doi: 10.3969/j.issn.1001-9960.2014.11.070
[24]	劉愛華, 劉銀朋, 程力. 三元混合模型在地下礦山涌水水源計算分析中的應用. 中南大學學報(自然科學版), 2014, 45(8):2768 Liu A H, Liu Y P, Cheng L. Application of ternary mixture model in discrimination of underground mine water in rush. J Central S Univ Sci Technol, 2014, 45(8): 2768
[25]	Yang B B, Sui W H, Duan L H. Risk assessment of water inrush in an underground coal mine based on GIS and fuzzy set theory. Mine Water Environ, 2017, 36(4): 617 doi: 10.1007/s10230-017-0457-1
[26]	李國慶, 馬鳳山, 孟召平. 新立礦區海底金屬礦坑與上覆海水的連通性分析. 中南大學學報(自然科學版), 2012, 43(10):3938 Li G Q, Ma F S, Meng Z P. Analysis of connectivity between undersea metal mine and overlying seawater in Xinli mine area. J Central S Univ Sci Technol, 2012, 43(10): 3938
[27]	李國慶, 汪新慶, 尹改梅. 主成分分析法在判定新立礦井海水滲入中的應用. 中國地質災害與防治學報, 2014, 25(3):83 Li G Q, Wang X Q, Yin G M. Application of principal component analysis in identifying the seepage of seawater into Xinli mine pit. Chin J Geol Hazard Control, 2014, 25(3): 83
[28]	Sun W J, Zhou W F, Jiao J. Hydrogeological classification and water inrush accidents in China’s coal mines. Mine Water Environ, 2016, 35(2): 214 doi: 10.1007/s10230-015-0363-3