Discrimination of Mine Water Bursting Source Based on Fuzzy System

Abstract:

Through applying the background values of aquifer derived from fuzzy clustering analysis, a fuzzy comprehensive estimation model was developed for quick recognition of mine water inrush. Based on the hydrological-chemical analysis data of water samples which water bursting sources were known in Liliu mining area, Shanxi province, this paper presented that the hydrological-chemical characters of different aquifer was different, and established a sort of fuzzy comprehensive evaluation models of discriminating coal mine water bursting sources in Liliu mining area. Applied to a production mine, the correct rate of water bursting source judged results by various methods was more than 70%. With the dispersion method and the method extracted from stepwise discrimination analysis to determine the membership degree and Model 3 the type determined by various factors, the correct rate of water bursting source with comprehensive evaluation of combination of two methods was higher respectively 94.5% and 93.3%. The fuzzy system can efficiently and accurately discriminate the resource of water inrush for an unknown sample, and provide the decision basis for the safety production of the coal mine.

• Periodical: Applied Mechanics and Materials (Volumes 182-183)
• Pages: 644-648
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.182-183.644
• Online since: June 2012
• Authors: Wei Feng Yang, Ding Yi Shen, Yu Bing Ji, Yi Wang
• Keywords: Discrimination, Fuzzy Comprehensive Estimation Model, Fuzzy System, Mine Water Inrush

References

[1] G. Tsekourasa, H. Sarimveisb, E. Kavaklia. A hierarchical fuzzy-clustering approach to fuzzy modeling. Fuzzy Sets and Systems 150, 2005, pp.245-266.

DOI: 10.1016/j.fss.2004.04.013

[2] W. X. Li. The application of fuzzy theory in mining and geotechnical engineering. China Metallurgical Industry Press, (1998).

[3] Y. Zhang. The Fuzzy Mathematics Method and Its Applications. China Coal Industry Press, (1991).

[4] A.F. Gomez-Skarmeta, M. Delgado, M.A. Vila. About the use of fuzzy clustering techniques for fuzzy model identi3cation. Fuzzy Sets and Systems 106, 1999, p.179–188.

DOI: 10.1016/s0165-0114(97)00276-5

[5] J.A. Dickerson, B. Kosko. Fuzzy function approximation with ellipsoidal rules. IEEE Trans. System Man and Cybernet. SMC-26 vol. 4, 1996, p.542–560.

DOI: 10.1109/3477.517030

[6] F. Klawonn, R. Kruse. Constructing a fuzzy controller from data. Fuzzy Sets and Systems 85, 1997, p.177–193.

DOI: 10.1016/0165-0114(95)00350-9