Please wait a minute...
img img
高级检索
地球科学进展  2004, Vol. 19 Issue (5): 860-866    DOI: 10.11867/j.issn.1001-8166.2004.05.0860
新学科·新技术·新发现     
神经网络分析方法在瓦斯预测中的应用
吴财芳;曾勇;秦勇
中国矿业大学资源与地球科学学院,江苏 徐州 221008
THE APPLICATION OF THE ANALYTIC METHODS OF NEURAL NETWORKS TO GAS-FORECASTING FIELD
WU Cai-fang, ZENG Yong, QIN Yong
Resource Engineering And Earth Science College, China University of Mining and Technology, Xuzhou 221008, China
 全文: PDF(96 KB)  
摘要:

论述了瓦斯预测技术的研究现状及其在现代矿业中面临的新问题,介绍了神经网络技术在处理复杂地质条件方面的优越性,探讨了瓦斯预测技术与人工神经网络等高新技术相结合的可能性与必要性,并举例论证了它们在瓦斯预测过程中的适用性。实践证明:瓦斯预测技术与人工神经网络相结合所建立的预测模型,不仅能够综合考虑各种影响因素,较好地处理地质条件中的各种非线性关系,而且预测精度高,结论可靠,为瓦斯预测技术的进一步发展提供了新的思路。

关键词: 神经网络瓦斯预测瓦斯含量瓦斯涌出量煤与瓦斯突出    
Abstract:

The research state of the gas-forecasting technologies and the new problems in the field of modern mining are explained. The advantage of neural networks in dealing with the complicated geological factors is introduced, and the possibility and necessity of combining the gas-forecasting technologies and the high, new techniques of artificial intelligence are discussed. The paper brings forward several new methods and gives examples to demonstrate their applicability in the process of forecasting coal and gas outburst. Past work proves that the forecasting models founded
 and based on  the gas-forecasting technology and artificial neural network can not only consider many affecting factors roundly and deal with all non-linear connections in geologic conditions preferably, but also have high precision and reliable conclusions, which offer new thought for the further developments of the gas-forecasting technologies.

Key words: Neural networks    Gas forecast    Gas content    Gas gushing quantity    Coal and gas outburst
收稿日期: 2003-06-06 出版日期: 2004-10-01
:  TD712  
通讯作者: 吴财芳(1976-),男,山东烟台人,博士后,主要从事瓦斯、煤层气地质与人工智能的研究.     E-mail: E-mail:caifangwu@sina.com
作者简介: 吴财芳(1976-),男,山东烟台人,博士后,主要从事瓦斯、煤层气地质与人工智能的研究.E-mail:caifangwu@sina.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
吴财芳
曾勇
秦勇

引用本文:

吴财芳;曾勇;秦勇. 神经网络分析方法在瓦斯预测中的应用[J]. 地球科学进展, 2004, 19(5): 860-866.

WU Cai-fang, ZENG Yong, QIN Yong. THE APPLICATION OF THE ANALYTIC METHODS OF NEURAL NETWORKS TO GAS-FORECASTING FIELD. Advances in Earth Science, 2004, 19(5): 860-866.

链接本文:

http://www.adearth.ac.cn/CN/10.11867/j.issn.1001-8166.2004.05.0860        http://www.adearth.ac.cn/CN/Y2004/V19/I5/860

[1]Zhou Shining(周世宁), Xian Xuefu(鲜学福), Zhu Wangxi(朱旺喜). The Stratagem Discussion of The Prevention and Cure Theory of Gas Disaster in Coal Mine[M]. Xuzhou: China University of Mining and Technology Press, 2001(in Chinese).
[2]Zhang Zixu(张子戍), Yuan Chongfu(袁崇孚). Study on mathematical model of coalbed gas geology used to prediction of mine gas emission[J]. Journal of China Coal Society(煤炭学报), 1999, 24(4): 368-372(in Chinese).
[3]Obaje N G, Abaa S I. Potential for coal-derived gaseous hydrocarbons in the middle Benue Trough of Nigeria[J]. Journal of Petroleum Geology, 1996, 19(1) : 77-94.
[4]Littke G S, Buker C, Luckye AA new evaluation of palaeo-heat flows and eroded thickness for the Carboniferous Ruhr basin[J]. Western Germany, International Journal of Soal Geology, 1994, 26 (1): 153-183.
[5]Wu Caifang(吴财芳), Zeng Yong(曾勇). The genetic neural networks and gas content forecast[J]. Earth Science Fronitiers(地学前缘), 2003, 10(1): 219-224(in Chinese). 
[6]He Xingui(何新贵). The New Development of Artificial Intelligence[M]. Beijing: Tsinghua University Press, 1994(in Chinese).
[7]Li Dawei(李大卫), Wang Mengguang(王梦光). A modified amalgamate GA[J]. Information and Control(信息与控制), 1997, 26(6): 449-454(in Chinese).
[8]Wang Xiaoping(王小平), Cao Liming(曹立明). GA-theory, Applications and Software Achievement[M]. Xi'an: Xi'an Jiaotong University Press, 2002(in Chinese).
[9]Wu Caifang, Zeng Yong, Zhang Xuliang. Application of the third theory of quantification in screening sensitive geological factors influencing coal and gas outburst[J]. Journal of China University of Mining & Technology, 2003, 13(1): 66-71.
[10]Pan Jienan(潘结南), Chen Jiangfeng(陈江峰). R/S analysis and fractal prediction of gas emission in coal mine[J]. Coal Geology and Exploration(煤田地质与勘探), 2001, 29(3): 14-15(in Chinese).
[11]Donald L, Turcotte. Fractals and Chaos in Geology and Geophysics[M]. Cambridge University Press, 1997. 158-162.
[12]Ling Yiying(凌怡莹), Xu Jianhua(徐建华). A nonlinear study on the urban system in Yangtze delta based on the fractal theory and the konhonen net[J]. Advances in Earth Science(地球科学进展), 2003, 18(4): 521-526(in Chinese).
[13]Sun Hongquan(孙洪泉), Xie Heping(谢和平). Fractal and statistical study of the fault attitude and roughness surface[J]. Journal of China Coal Society(煤炭学报), 1999, 24(6): 571-575(in Chinese).
[14]Liu Mingju, Liu Xiliang, He Jun. Fractal prediction research of coal and gas geology[J]. Journal of China Coal Society, 1998, 23(6): 616-619.
[15]Wang Shitong(王士同). Fuzzy System, Fuzzy NN and Their Applying Software Projection[M]. Shanghai: Press House of Shanghai Science and Technology Literature, 1997(in Chinese). 
[16]Zhang Zixu, Wu Caifang, Yuan Chongfu. The technology of fuzzy-neural networks applying to forecast the coal-gas outburst[A]. In:Proceedings in Mining Science and Safety Technology[C]. Beijing: Science Press, 2002. 458-462.
[17]Wu Caifang(吴财芳), Zeng Yong(曾勇), Zhang Zixu(张子戌), et al. The fuzzy-neural networks and theory of forecasting the coal-gas-outburst[J]. Coal Geology & Exploration(煤田地质与勘探), 2002, 30(6): 4-8(in Chinese).

[1] 陈科贵, 陈旭, 张家浩. 复合渗透率测井评价方法在砂砾岩稠油油藏的应用*——以克拉玛依油田某区八道湾组为例[J]. 地球科学进展, 2015, 30(7): 773-779.
[2] 李启权,王昌全,岳天祥,张文江,余勇. 基于神经网络模型的中国表层土壤有机质空间分布模拟方法[J]. 地球科学进展, 2012, 27(2): 175-184.
[3] 朱子先, 臧淑英. 基于遗传神经网络的克钦湖叶绿素反演研究[J]. 地球科学进展, 2012, 27(2): 202-208.
[4] 柴琳娜,屈永华,张立新,梁顺林,王锦地. 基于自回归神经网络的时间序列叶面积指数估算[J]. 地球科学进展, 2009, 24(7): 756-768.
[5] 王红丽,顾亚进,刘健,况雪源,提汝媛 . BP神经网络在古气候序列重建中的应用[J]. 地球科学进展, 2009, 24(11): 1275-1279.
[6] 李天斌,肖学沛. 地下工程岩爆预测的综合集成方法[J]. 地球科学进展, 2008, 23(5): 533-540.
[7] 赵苏璇,罗坚,杨成荫. 基于BP神经网络的气象格点数据无损压缩方法[J]. 地球科学进展, 2008, 23(2): 206-213.
[8] 哈斯巴干,马建文,李启青. ASTER数据的自组织神经网络分类研究[J]. 地球科学进展, 2003, 18(3): 345-350.
[9] 李双成,郑度. 人工神经网络模型在地学研究中的应用进展[J]. 地球科学进展, 2003, 18(1): 68-076.