Abstract
Accurately and effectively predicting the quantity of water inrush from the roof of coal mines is important for the safety of coal mine production. There is a complex and nonlinear relationship between the water inrush quantities from the coal roof and its influencing factors. To improve the precision and reliability in predicting the water inrush quantity, this paper establishes a water inrush quantity quantitative prediction model for coal seam roof aquifers based on the partial least squares regression (PLSR) and radial basis function (RBF) neural network coupling methods. First, the influencing factors of the coal roof water inrush quantity in the study area are determined, and then PLSR is used to reduce the dimensions of the original data by extracting the principal components with the best interpretation function for the system. The principal components are then used as input to the RBF neural network to model and predict the coal roof water inrush quantity, which effectively overcomes the multicollinearity problem between variables, optimizes the network structure, and improves the learning efficiency and robustness of the network. Finally, the reliability of the method is verified through simulation testing and comparison with other prediction methods. The results show that: compared with the PLSR model, the multiple linear regression (MLR) model, the RBF neural network model, the SVM model, and the FA-RBF neural network model, the fitting and prediction capabilities of the coal roof water inrush quantity prediction model based on the PLSR and the RBF neural network are better than the other models. The average absolute error of fitting of this model is 6.07E-4 m3/h, and the average relative error of fitting is 6.07E-3%; the average absolute error and the average relative error of prediction of this model for new samples are 1.9967 m3/h and 9.8730% respectively. The model combines the unique advantages of the PLSR and the RBF neural network and can deal with the correlation and nonlinear problems between variables, which is very practicable and provides a new way for predicting water inrush quantities from coal roofs.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.References
Cao QK, Zhao F (2011) Forecast of water inrush quantity from coal floor based on genetic algorithm-support vector regression. J Chin Coal Soc 36(12):2097–2101. https://doi.org/10.13225/j.cnki.jccs.2011.12.026
Chen JP, Wang CL, Wang XD (2021) Coal mine floor water inrush prediction based on CNN neural network. Chin J Geol Hazard Control 32(01):50–57. https://doi.org/10.16031/j.cnki.issn.1003-8035.2021.01.07
Chen G, Yang ZQ, Liu BQ (2015) A probabilistitic neural network classification algorithm based PLS. Microelectron Comput 32(05):73–78. https://doi.org/10.19304/j.cnki.issn1000-7180.2015.05.016
Chen NX, Cao LH, Li M, Huang Q (2005) Forecasting water yield of mine with the partial least square method and neural network. J Jilin Univ (eArth Sci Ed) 35(06):88–92. https://doi.org/10.13278/j.cnki.jjuese.2005.06.015
Chen HJ, Li XB, Liu AH, Dong LJ, Liu ZX (2009) Forecast method of water inrush quantity from coal floor based on distance discriminant analysis theory. J Chin Coal Soc 34(04):487–491. https://doi.org/10.13225/j.cnki.jccs.2009.04.014
Chen CH, Tan J, Yin JK, Zhang F, Yao J (2010) Prediction for soil moisture in tobacco fields based on PCA and RBF neural network. Trans Chin Soc Agric Eng 26(08):85–90. https://doi.org/10.3969/j.issn.1002-6819.2010.08.014
Cheng AP, Gao YT, Ji MW (2014) Wu P (2014) Forecast of water inrush from coal floor based on unascertained measure theory. Metal Mine 08:157–161. https://doi.org/10.3969/j.issn.1001-1250.2014.08.037
Cheng XG, Qiao W, Li GF, Yu ZQ (2021) Risk assessment of roof water disaster due to multi-seam mining at Wulunshan Coal Mine in China. Arab J Geosci 14(12):1116. https://doi.org/10.16031/10.1007/S12517-021-07491-8
Chu JC, Liu XY, Zhang ZW, Zhang YL, He MG (2021) A novel method overcomeing overfitting of artificial neural network for accurate prediction: application on thermophysical property of natural gas. Case Stud Thermal Eng 28:101406. https://doi.org/10.1016/j.csite.2021.101406
Dai QW, Jiang FP, Dong L (2014) RBFNN inversion for electrical resistivity tomography based on Hannan-Quinn criterion. Chin J Geophys 57(04):1335–1344. https://doi.org/10.6038/cjg20140430
Das AJ, Mandal PK, Sahu SP, Kushwaha A, Bhattacharjee R, Tewari S (2018) Evaluation of the effect of fault on the stability of underground workings of coal mine through DEM and statistical analysis. J Geol Soc India 92(6):732–742. https://doi.org/10.1007/s12594-018-1096-2
Dhiman HS, Deb D, Guerrero JM (2019) Hybrid machine intelligent SVR variants for wind forecasting and ramp events. Renew Sustain Energy Rev 108:369–379. https://doi.org/10.1016/j.rser.2019.04.002
Gao WD, Wang ZS (2012) Forecast of inrushed water volume grade from coal floor based on support vector machine with particle swarm optimization. Coal Geol Explor 40(06):44–47. https://doi.org/10.3969/j.issn.1001-1986.2012.06.010
Gao R, Yan H, Ju F, Mei XC, Wang XL (2018) Influential factors and control of water inrush in a coal seam as the main aquifer. Int J Min Sci Techno 28(02):187–193. https://doi.org/10.1016/j.ijmst.2017.12.017
Gong YW, Jiang CL, Wu AJ (2012) Prediction of mine water inrush based on multiple linear regression. Coal Technol 31(03):112–114. https://doi.org/10.3969/j.issn.1008-8725.2012.03.049
Gong B (2021) Study of PLSR-BP model for stability assessment of loess slope based on particle swarm optimization. Sci Rep-UK 11(1):17888. https://doi.org/10.1038/s41598-021-97484-0
Guan P, Jiao YY, Duan XS (2021) Non-liner prediction of soil thermal conductivity based on RBF neural network. Acta Energiae Solaris Sinica 42(03):171–178
Han J, Shi LQ, Zhai PH, Li SC, Yu XG (2009) Application of multi-attribute decision and D-S evidence theory to water-inrush decision of floor in mining. Chin J Rock Mech Eng 28(S2):3727–3732. https://doi.org/10.3321/j.issn:1000-6915.2009.z2.062
Hu XJ, Li WP, Cao DT, Liu MC (2012) Index of multiple factors and expected height of fully mechanized water flowing fractured zone. J Chin Coal Soc 37(04):613–620
Ji YD (2019) The risk assessment of roof water inrush based on cluster analysis and fuzzy comprehensive evaluation. Mining Saf Environ Protection 46(04):68–72. https://doi.org/10.3969/j.issn.1008-4495.2019.04.015
Jiang AN, Liang B (2005) Forecast of water inrush from coal floor based on least square support vector machine. J Chin Coal Soc 30(05):71–75. https://doi.org/10.3321/j.issn:0253-9993.2005.05.016
Ju QD, Hu YB (2021) Source identification of mine water inrush based on principal component analysis and grey situation decision. Environ Eartn Sci 80:157. https://doi.org/10.1007/s12665-021-09459-z
Kou JQ, Zhang WW (2015) Research on the effects of function widths of aerodynamic modeling based on recursive RBF neural network. Adv Aeronaut Sci Eng 6(3):261–270
Liu BZ, Liang B (2011) Prediction of seamfloor water inrush based on combining principal component analysis and support vector regression. Coal Geol Explor 39(01):28–30. https://doi.org/10.3969/j.issn.1001-1986.2011.01.007
LaMoreaux JW, Wu Q, Zhou WF (2014) New development in theory and practice in mine water control in China. Carbonates Evaporites 29:141–145. https://doi.org/10.1007/s13146-014-0204-7
Li HJ, Chen QT, Shu ZY, Li L, Zhang YC (2018) On prevention and mechanism of bed separation water inrush for thick coal seams: a case study in China. Environ Earth Sci 77(22):759. https://doi.org/10.1007/s12665-018-7952-y
Liu SL, Li WP (2019) Fuzzy comprehensive risk evaluation of roof water inrush based on catastrophe theory in the Jurassic coalfield of northwest China. J Intell & Fuzzy Syst 37(2):2101–2111. https://doi.org/10.3233/JIFS-171157
Liang Z, Wang YY, Yue YT, Wei FL, Jiang H, Li SC (2020) A coupling model of genetic algorithm and RBF neural network for the prediction of PM2.5 concentration. China Environ Sci 40(02):523–529
Liu WT, Zheng QS, Pang LF, Dou WM, Meng XX (2021) Study of roof water inrush forecasting based on EM-FAHP two-factor model. Math Biosci Eng 18(5):4987–5005. https://doi.org/10.3934/MBE.2021254
Ma D, Duan HY, Cai X, Li ZH, Li Q, Zhang Q (2018) A global optimization-based method for the prediction of water inrush hazard from mining floor. Water 10(11):1618. https://doi.org/10.3390/w10111618
Montoya-Chairez J, Rossomando FG, Carelli R, Santibanez V, Moreno-Valenzuela J (2021) Adaptive RBF neural network-based control of an underactuated control moment gyroscope. Neural Comput Appl 33(12):6805–6818. https://doi.org/10.1007/s00521-020-05456-8
Peng BB, Yan XG, Du J (2020) Surface quality prediction based on BP and RBF neural networks. Surface Technol 49(10):324–328. https://doi.org/10.16490/j.cnki.issn.1001-3660.2020.10.038
Qin J, Li C, Li Z, Zhao Y (2013) Prediction of mine water inrush quantity based on support vector regression. China Saf Sci J 23(05):114–119. https://doi.org/10.16265/j.cnki.issn1003-3033.2013.05.022
Roushangar K, Koosheh A (2015) Evaluation of GA-SVR method for modeling bed load transport in gravel-bed rivers. J Hydrol 527:1142–1152. https://doi.org/10.1016/j.jhydrol.2015.06.006
Shi XZ, Wu YM, Tang LZ, Huang XD (2013) Application of neural network model with partial least-square regression in prediction of peak velocity of blasting vibration. J Vib Shock 32(12):45–49. https://doi.org/10.13465/j.cnki.jvs.2013.12.008
Shi WH, Yang TH, Yu QL, Li Y, Liu HL, Zhao YC (2017) A study of water-inrush mechanisms based on geo-mechanical analysis and an in-situ groundwater investigation in the Zhongguan Iron Mine, China. Mine Water Environ 36(3):409–417. https://doi.org/10.1007/s10230-017-0429-5
Su KX, Zhang JW, Li X, Zhang JX, Zhu SD, Yi KJ (2020) Prediction of fatigue life and residual stress relaxation behavior of shot-peened 25CrMo axle steel based on neural network. Rare Metal Mater Eng 49(08):2697–2705
Tong ZH, Liu WY, Han CH, Qi ZF (2013) Research on the evaluation of enterprise knowledge integration capability based on Fussy-RBF. Info Stud Theory Appl 36(08):51–56
Tao JL, Yu Z, Zhang RD, Guo FR (2021) RBF neural network modeling approach using PCA based LM-GA optimization for coke furnace system. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2021.107691
Wang KL, Xiong HG, Zhang F (2014) PLSR-BP complex model-based hyper-spectrum retrieval of oasis soil pH. Arid Zone Res 31(06):1005–1009
Wei DZ, Chen FJ, Zheng XX (2015) Internet public opinion chaotic prediction based on chaos theory and the improved radial basis function in neural networks. Acta Physica Sinica 64(11):52–59. https://doi.org/10.7498/aps.64.110503
Wu Q, Xu K, Zhang W (2016) Further research on “three maps-two predictions” method for prediction on coal seam roof water bursting risk. J Chin Coal Soc 41(06):1341–1347. https://doi.org/10.13225/j.cnki.jccs.2015.1210
Wu Q, Shen JJ, Liu WT, Wang Y (2017) A RBFNN-based method for the prediction of the developed height of a water-conductive fractured zone for fully mechanized mining with sublevel caving. Arab J Geosci 10(7):1–9. https://doi.org/10.1007/s12517-017-2959-3
Wen TX, Sun X, Tian HB, Kong XB (2017) Prediction of the water inrush from the coal seam based on PCA-Fuzzy-RF model. J Saf Environ 17(3):855–858. https://doi.org/10.13637/j.issn.1009-6094.2017.03.009
Wang XH, Zhu SY, Yu HT, Liu YX (2021) Comprehensive analysis control effect of faults on the height of fractured water-conducting zone in longwall mining. Nat Hazards 108(2):2143–2165. https://doi.org/10.1007/s11069-021-04772-z
Xiao JY, Tong MM, Jiang CL (2012) Prediction of water inrush quantity from coal floor based on fuzzy evidence theory. J Chin Coal Soc 37(S1):131–137. https://doi.org/10.13225/j.cnki.jccs.2012.s1.032
Xu ZM, Sun YJ, Gao S, Zhao XM, Duan RQ, Yao MH, Liu Q (2018) Groundwater source discrimination and proportion determination of mine inflow using ion analyses: a case study from the Longmen Coal Mine, Henan Province, China. Mine Water Environ 37:385–392. https://doi.org/10.1007/s10230-018-0512-6
Yan CB, Wang HJ, Yang JH, Chen K, Zhou JJ, Guo WX (2021) Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network. Rock Soil Mech 42(02):519–528. https://doi.org/10.16285/j.rsm.2020.0164
Yang ZL, Meng XR, Wang XQ, Wang KY (2013) Nonlinear prediction and evaluation of coal mine floor water inrush based on GA-BP neural network model. Saf Coal Mines 44(02):36–39. https://doi.org/10.13347/j.cnki.mkaq.2013.02.024
Yang Q, Ye ZF, Li XZ, Wei DZ, Chen SH, Li ZR (2021) Prediction of flight status of logistics UAVs based on an information entropy radial basis function neural network. Sensors 21(11):3651. https://doi.org/10.3390/s21113651
Yin HY, Shi YL, Niu HG, Xie DL, Wei JC, Lefticariu L, Xu SX (2018) A GIS-based model of potential groundwater yield zonation for a sandstone aquifer in the Juye Coalfield, Shangdong, China. J Hydrol 557:434–447. https://doi.org/10.1016/j.jhydrol.2017.12.043
Yin HY, Zhao H, Xie DL, Sang SZ, Shi YL, Tian MH (2019) Mechanism of mine water inrush from overlying porous aquifer in Quaternary: a case study in Xinhe Coal Mine of Shandong Province. China Arab J Geosci 12(05):163. https://doi.org/10.1007/s12517-019-4325-0
Zeng YF, Wu Q, Liu SQ, Zhai YL, Lian HQ, Zhang W (2018) Evaluation of a coal seam roof water inrush: case study in the Wangjialing coal mine, China. Mine Water Environ 1(37):174–184. https://doi.org/10.1007/s10230-017-0459-z
Zhang J, Yang T (2018) Study of a roof water inrush prediction model in shallow seam mining based on an analytic hierarchy process using a grey relational analysis method. Arab J Geosci 11(7):153. https://doi.org/10.1007/s12517-018-3498-2
Zhang YG, Yang LN (2021) A novel dynamic predictive method of water inrush from coal floor based on gated recurrent unit model. Nat Hazards 105(02):2027–2043. https://doi.org/10.1007/S11069-020-04388-9
Zhang P, Zhang JX, Zhang ZH (2020) Design of RBFNN-based adaptive sliding mode control strategy for active rehabilitation robot. IEEE Access 8:155538–155547. https://doi.org/10.1109/ACCESS.2020.3018737
Zhang YW, Zhang LL, Li HJ, Chi BM (2021a) Evaluation of the water yield of coal roof aquifers based on the FDAHP-Entropy method: A case study in the Donghuantuo Coal Mine. China Geofluids 2021:5512729. https://doi.org/10.1155/2021/5512729
Zhang ZC, Gao TY, Zhang L, Tuo SF (2021b) Aeroheating agent model based on radial basis function neural network. Acta Aeronautica Et Astronautica Sinica 42(04):303–312. https://doi.org/10.7527/S1000-6893.2020.24167
Zhao DK, Wu Q (2018) An approach to predict the height of fractured water-conducting zone of coal roof strata using random forest regression. Sci Rep-UK 8(1):10986. https://doi.org/10.1038/s41598-018-29418-2
Zheng K, Jia XY, Liao WH (2013) Wear loss prediction model of denture material based on radial basis function neural network. J Nanjing Univ Sci Technol 37(06):922–925. https://doi.org/10.14177/j.cnki.32-1397n.2013.06.020
Funding
The study was supported by the National Natural Science Foundation of China (Grant No. 41272278) and the Scientific Research Platform Innovation Team Construction Project in Universities of Anhui (Grant No. 2016-2018-24).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bi, Y., Wu, J. & Zhai, X. Quantitative prediction model of water inrush quantities from coal mine roofs based on multi-factor analysis. Environ Earth Sci 81, 314 (2022). https://doi.org/10.1007/s12665-022-10432-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12665-022-10432-7